From 94ac2ab3fff96814d7460a27a0e9d004abbd4128 Mon Sep 17 00:00:00 2001
From: Daniel Baumann <daniel.baumann@progress-linux.org>
Date: Wed, 19 Jun 2024 23:00:37 +0200
Subject: Merging upstream version 6.9.2.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
---
 tools/testing/selftests/bpf/DENYLIST.aarch64       |    3 +-
 tools/testing/selftests/bpf/DENYLIST.s390x         |    3 +
 tools/testing/selftests/bpf/Makefile               |   51 +-
 tools/testing/selftests/bpf/README.rst             |   32 +-
 tools/testing/selftests/bpf/bench.c                |   40 +-
 tools/testing/selftests/bpf/benchs/bench_trigger.c |  182 +++-
 .../selftests/bpf/benchs/run_bench_uprobes.sh      |    9 +
 tools/testing/selftests/bpf/bpf_arena_alloc.h      |   67 ++
 tools/testing/selftests/bpf/bpf_arena_common.h     |   70 ++
 tools/testing/selftests/bpf/bpf_arena_htab.h       |  100 ++
 tools/testing/selftests/bpf/bpf_arena_list.h       |   92 ++
 tools/testing/selftests/bpf/bpf_experimental.h     |   76 +-
 tools/testing/selftests/bpf/bpf_kfuncs.h           |   30 +-
 .../testing/selftests/bpf/bpf_test_no_cfi/Makefile |   19 +
 .../bpf/bpf_test_no_cfi/bpf_test_no_cfi.c          |   84 ++
 .../selftests/bpf/bpf_testmod/bpf_testmod.c        |  123 ++-
 .../selftests/bpf/bpf_testmod/bpf_testmod.h        |   65 ++
 tools/testing/selftests/bpf/cgroup_helpers.c       |    3 -
 tools/testing/selftests/bpf/config                 |    1 +
 tools/testing/selftests/bpf/network_helpers.c      |    2 -
 .../testing/selftests/bpf/prog_tests/arena_htab.c  |   90 ++
 .../testing/selftests/bpf/prog_tests/arena_list.c  |   71 ++
 .../selftests/bpf/prog_tests/bad_struct_ops.c      |   67 ++
 .../selftests/bpf/prog_tests/bpf_verif_scale.c     |    2 +-
 tools/testing/selftests/bpf/prog_tests/btf.c       |   29 +
 .../selftests/bpf/prog_tests/cgroup1_hierarchy.c   |    7 +-
 tools/testing/selftests/bpf/prog_tests/cpumask.c   |    6 +-
 .../testing/selftests/bpf/prog_tests/ctx_rewrite.c |   44 -
 .../selftests/bpf/prog_tests/decap_sanity.c        |    2 +-
 .../testing/selftests/bpf/prog_tests/fib_lookup.c  |    2 +-
 .../selftests/bpf/prog_tests/fill_link_info.c      |  114 ++-
 .../selftests/bpf/prog_tests/ip_check_defrag.c     |    4 +-
 .../selftests/bpf/prog_tests/kptr_xchg_inline.c    |   52 +
 .../selftests/bpf/prog_tests/libbpf_probes.c       |    4 +
 .../testing/selftests/bpf/prog_tests/libbpf_str.c  |    6 +
 tools/testing/selftests/bpf/prog_tests/log_fixup.c |    4 +-
 .../testing/selftests/bpf/prog_tests/lwt_helpers.h |    2 -
 .../selftests/bpf/prog_tests/lwt_redirect.c        |    3 +-
 .../testing/selftests/bpf/prog_tests/lwt_reroute.c |    3 +-
 tools/testing/selftests/bpf/prog_tests/mptcp.c     |    2 +-
 .../selftests/bpf/prog_tests/rcu_read_lock.c       |    6 +
 .../testing/selftests/bpf/prog_tests/reg_bounds.c  |    2 +-
 .../selftests/bpf/prog_tests/sock_destroy.c        |    2 +-
 .../selftests/bpf/prog_tests/sock_iter_batch.c     |    4 +-
 tools/testing/selftests/bpf/prog_tests/spin_lock.c |    2 +
 .../bpf/prog_tests/struct_ops_autocreate.c         |  159 +++
 .../selftests/bpf/prog_tests/task_local_storage.c  |    6 -
 .../bpf/prog_tests/tcp_custom_syncookie.c          |  150 +++
 .../bpf/prog_tests/test_struct_ops_maybe_null.c    |   46 +
 .../bpf/prog_tests/test_struct_ops_module.c        |  101 ++
 .../bpf/prog_tests/test_struct_ops_multi_pages.c   |   30 +
 .../bpf/prog_tests/test_struct_ops_no_cfi.c        |   35 +
 .../testing/selftests/bpf/prog_tests/test_tunnel.c |   18 +-
 tools/testing/selftests/bpf/prog_tests/token.c     | 1052 ++++++++++++++++++++
 .../selftests/bpf/prog_tests/tracing_failure.c     |   37 +
 tools/testing/selftests/bpf/prog_tests/verifier.c  |    6 +
 .../selftests/bpf/prog_tests/xdp_do_redirect.c     |    4 +-
 tools/testing/selftests/bpf/prog_tests/xdpwall.c   |    2 +-
 tools/testing/selftests/bpf/progs/arena_htab.c     |   48 +
 tools/testing/selftests/bpf/progs/arena_htab_asm.c |    5 +
 tools/testing/selftests/bpf/progs/arena_list.c     |   87 ++
 .../selftests/bpf/progs/async_stack_depth.c        |    4 +-
 tools/testing/selftests/bpf/progs/bad_struct_ops.c |   25 +
 .../testing/selftests/bpf/progs/bad_struct_ops2.c  |   14 +
 .../bpf/progs/bench_local_storage_create.c         |    5 +-
 tools/testing/selftests/bpf/progs/bpf_compiler.h   |   33 +
 tools/testing/selftests/bpf/progs/bpf_misc.h       |    2 +-
 .../testing/selftests/bpf/progs/bpf_tracing_net.h  |   16 +
 .../selftests/bpf/progs/cgrp_ls_recursion.c        |   26 -
 .../selftests/bpf/progs/connect_unix_prog.c        |    3 +-
 tools/testing/selftests/bpf/progs/cpumask_common.h |   57 +-
 .../selftests/bpf/progs/getpeername_unix_prog.c    |    3 +-
 .../selftests/bpf/progs/getsockname_unix_prog.c    |    3 +-
 tools/testing/selftests/bpf/progs/iters.c          |    9 +-
 .../testing/selftests/bpf/progs/kptr_xchg_inline.c |   48 +
 tools/testing/selftests/bpf/progs/local_storage.c  |   20 +-
 tools/testing/selftests/bpf/progs/loop4.c          |    4 +-
 tools/testing/selftests/bpf/progs/lsm_cgroup.c     |    8 +-
 tools/testing/selftests/bpf/progs/map_ptr_kern.c   |    2 +-
 tools/testing/selftests/bpf/progs/priv_map.c       |   13 +
 tools/testing/selftests/bpf/progs/priv_prog.c      |   13 +
 tools/testing/selftests/bpf/progs/profiler.inc.h   |   17 +-
 tools/testing/selftests/bpf/progs/pyperf.h         |    7 +-
 tools/testing/selftests/bpf/progs/rcu_read_lock.c  |  120 +++
 .../selftests/bpf/progs/recvmsg_unix_prog.c        |    3 +-
 .../selftests/bpf/progs/sendmsg_unix_prog.c        |    3 +-
 .../selftests/bpf/progs/sk_storage_omem_uncharge.c |    4 +-
 .../testing/selftests/bpf/progs/sock_iter_batch.c  |    4 +-
 tools/testing/selftests/bpf/progs/strobemeta.h     |   18 +-
 .../selftests/bpf/progs/struct_ops_autocreate.c    |   52 +
 .../selftests/bpf/progs/struct_ops_autocreate2.c   |   32 +
 .../selftests/bpf/progs/struct_ops_maybe_null.c    |   29 +
 .../bpf/progs/struct_ops_maybe_null_fail.c         |   24 +
 .../selftests/bpf/progs/struct_ops_module.c        |   56 ++
 .../selftests/bpf/progs/struct_ops_multi_pages.c   |  102 ++
 .../selftests/bpf/progs/task_ls_recursion.c        |   17 -
 .../selftests/bpf/progs/test_cls_redirect.c        |    7 +-
 .../selftests/bpf/progs/test_cls_redirect_dynptr.c |    2 +
 .../selftests/bpf/progs/test_core_reloc_type_id.c  |    2 +-
 .../selftests/bpf/progs/test_fill_link_info.c      |    6 +
 .../selftests/bpf/progs/test_global_func1.c        |    8 +-
 .../bpf/progs/test_global_func_ctx_args.c          |   19 +
 .../selftests/bpf/progs/test_lwt_seg6local.c       |    6 +-
 .../selftests/bpf/progs/test_ptr_untrusted.c       |    6 +-
 tools/testing/selftests/bpf/progs/test_seg6_loop.c |    4 +-
 tools/testing/selftests/bpf/progs/test_siphash.h   |   64 ++
 tools/testing/selftests/bpf/progs/test_skb_ctx.c   |    4 +-
 tools/testing/selftests/bpf/progs/test_spin_lock.c |   65 ++
 .../selftests/bpf/progs/test_spin_lock_fail.c      |   44 +
 .../selftests/bpf/progs/test_sysctl_loop1.c        |    6 +-
 .../selftests/bpf/progs/test_sysctl_loop2.c        |    6 +-
 .../testing/selftests/bpf/progs/test_sysctl_prog.c |    6 +-
 tools/testing/selftests/bpf/progs/test_tc_tunnel.c |    5 +-
 .../bpf/progs/test_tcp_custom_syncookie.c          |  595 +++++++++++
 .../bpf/progs/test_tcp_custom_syncookie.h          |  140 +++
 .../testing/selftests/bpf/progs/test_tcpbpf_kern.c |    2 +-
 tools/testing/selftests/bpf/progs/test_xdp.c       |    3 +-
 .../testing/selftests/bpf/progs/test_xdp_dynptr.c  |   10 +-
 tools/testing/selftests/bpf/progs/test_xdp_loop.c  |    3 +-
 .../selftests/bpf/progs/test_xdp_noinline.c        |    5 +-
 tools/testing/selftests/bpf/progs/token_lsm.c      |   32 +
 .../testing/selftests/bpf/progs/tracing_failure.c  |   20 +
 tools/testing/selftests/bpf/progs/trigger_bench.c  |   28 +
 tools/testing/selftests/bpf/progs/type_cast.c      |   13 +-
 tools/testing/selftests/bpf/progs/verifier_arena.c |  150 +++
 .../selftests/bpf/progs/verifier_arena_large.c     |   68 ++
 .../bpf/progs/verifier_direct_packet_access.c      |    2 +-
 .../selftests/bpf/progs/verifier_global_ptr_args.c |  182 ++++
 .../selftests/bpf/progs/verifier_global_subprogs.c |   29 +
 .../bpf/progs/verifier_iterating_callbacks.c       |  103 +-
 .../testing/selftests/bpf/progs/verifier_loops1.c  |   24 +
 .../selftests/bpf/progs/verifier_spill_fill.c      |  553 +++++++++-
 .../selftests/bpf/progs/verifier_spin_lock.c       |    2 +-
 .../selftests/bpf/progs/xdp_synproxy_kern.c        |    6 +-
 tools/testing/selftests/bpf/progs/xdping_kern.c    |    3 +-
 tools/testing/selftests/bpf/test_loader.c          |   13 +-
 tools/testing/selftests/bpf/test_lpm_map.c         |   18 +-
 tools/testing/selftests/bpf/test_progs.c           |   77 +-
 tools/testing/selftests/bpf/test_progs.h           |   10 +-
 tools/testing/selftests/bpf/test_sock_addr.c       |    3 +-
 tools/testing/selftests/bpf/test_sockmap.c         |    2 +-
 tools/testing/selftests/bpf/test_verifier.c        |   60 +-
 tools/testing/selftests/bpf/testing_helpers.c      |   96 +-
 tools/testing/selftests/bpf/testing_helpers.h      |   10 +
 .../selftests/bpf/verifier/bpf_loop_inline.c       |    6 +
 tools/testing/selftests/bpf/verifier/precise.c     |    6 +-
 tools/testing/selftests/bpf/xdp_hw_metadata.c      |    2 +-
 147 files changed, 6204 insertions(+), 496 deletions(-)
 create mode 100755 tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh
 create mode 100644 tools/testing/selftests/bpf/bpf_arena_alloc.h
 create mode 100644 tools/testing/selftests/bpf/bpf_arena_common.h
 create mode 100644 tools/testing/selftests/bpf/bpf_arena_htab.h
 create mode 100644 tools/testing/selftests/bpf/bpf_arena_list.h
 create mode 100644 tools/testing/selftests/bpf/bpf_test_no_cfi/Makefile
 create mode 100644 tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c
 create mode 100644 tools/testing/selftests/bpf/prog_tests/arena_htab.c
 create mode 100644 tools/testing/selftests/bpf/prog_tests/arena_list.c
 create mode 100644 tools/testing/selftests/bpf/prog_tests/bad_struct_ops.c
 create mode 100644 tools/testing/selftests/bpf/prog_tests/kptr_xchg_inline.c
 create mode 100644 tools/testing/selftests/bpf/prog_tests/struct_ops_autocreate.c
 create mode 100644 tools/testing/selftests/bpf/prog_tests/tcp_custom_syncookie.c
 create mode 100644 tools/testing/selftests/bpf/prog_tests/test_struct_ops_maybe_null.c
 create mode 100644 tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c
 create mode 100644 tools/testing/selftests/bpf/prog_tests/test_struct_ops_multi_pages.c
 create mode 100644 tools/testing/selftests/bpf/prog_tests/test_struct_ops_no_cfi.c
 create mode 100644 tools/testing/selftests/bpf/prog_tests/token.c
 create mode 100644 tools/testing/selftests/bpf/prog_tests/tracing_failure.c
 create mode 100644 tools/testing/selftests/bpf/progs/arena_htab.c
 create mode 100644 tools/testing/selftests/bpf/progs/arena_htab_asm.c
 create mode 100644 tools/testing/selftests/bpf/progs/arena_list.c
 create mode 100644 tools/testing/selftests/bpf/progs/bad_struct_ops.c
 create mode 100644 tools/testing/selftests/bpf/progs/bad_struct_ops2.c
 create mode 100644 tools/testing/selftests/bpf/progs/bpf_compiler.h
 create mode 100644 tools/testing/selftests/bpf/progs/kptr_xchg_inline.c
 create mode 100644 tools/testing/selftests/bpf/progs/priv_map.c
 create mode 100644 tools/testing/selftests/bpf/progs/priv_prog.c
 create mode 100644 tools/testing/selftests/bpf/progs/struct_ops_autocreate.c
 create mode 100644 tools/testing/selftests/bpf/progs/struct_ops_autocreate2.c
 create mode 100644 tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c
 create mode 100644 tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c
 create mode 100644 tools/testing/selftests/bpf/progs/struct_ops_module.c
 create mode 100644 tools/testing/selftests/bpf/progs/struct_ops_multi_pages.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_siphash.h
 create mode 100644 tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.h
 create mode 100644 tools/testing/selftests/bpf/progs/token_lsm.c
 create mode 100644 tools/testing/selftests/bpf/progs/tracing_failure.c
 create mode 100644 tools/testing/selftests/bpf/progs/verifier_arena.c
 create mode 100644 tools/testing/selftests/bpf/progs/verifier_arena_large.c
 create mode 100644 tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c

(limited to 'tools/testing/selftests/bpf')

diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64
index 5c2cc7e8c5..d8ade15e27 100644
--- a/tools/testing/selftests/bpf/DENYLIST.aarch64
+++ b/tools/testing/selftests/bpf/DENYLIST.aarch64
@@ -1,6 +1,5 @@
 bpf_cookie/multi_kprobe_attach_api               # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3
 bpf_cookie/multi_kprobe_link_api                 # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3
-exceptions					 # JIT does not support calling kfunc bpf_throw: -524
 fexit_sleep                                      # The test never returns. The remaining tests cannot start.
 kprobe_multi_bench_attach                        # needs CONFIG_FPROBE
 kprobe_multi_test                                # needs CONFIG_FPROBE
@@ -11,3 +10,5 @@ fill_link_info/kprobe_multi_link_info            # bpf_program__attach_kprobe_mu
 fill_link_info/kretprobe_multi_link_info         # bpf_program__attach_kprobe_multi_opts unexpected error: -95
 fill_link_info/kprobe_multi_invalid_ubuff        # bpf_program__attach_kprobe_multi_opts unexpected error: -95
 missed/kprobe_recursion                          # missed_kprobe_recursion__attach unexpected error: -95 (errno 95)
+verifier_arena                                   # JIT does not support arena
+arena_htab                                       # JIT does not support arena
diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x
index 1a63996c03..f4a2f66a68 100644
--- a/tools/testing/selftests/bpf/DENYLIST.s390x
+++ b/tools/testing/selftests/bpf/DENYLIST.s390x
@@ -3,3 +3,6 @@
 exceptions				 # JIT does not support calling kfunc bpf_throw				       (exceptions)
 get_stack_raw_tp                         # user_stack corrupted user stack                                             (no backchain userspace)
 stacktrace_build_id                      # compare_map_keys stackid_hmap vs. stackmap err -2 errno 2                   (?)
+verifier_iterating_callbacks
+verifier_arena                           # JIT does not support arena
+arena_htab                               # JIT does not support arena
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index fd15017ed3..3b9eb40d63 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -34,13 +34,26 @@ LIBELF_CFLAGS	:= $(shell $(PKG_CONFIG) libelf --cflags 2>/dev/null)
 LIBELF_LIBS	:= $(shell $(PKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf)
 
 CFLAGS += -g $(OPT_FLAGS) -rdynamic					\
-	  -Wall -Werror 						\
+	  -Wall -Werror -fno-omit-frame-pointer				\
 	  $(GENFLAGS) $(SAN_CFLAGS) $(LIBELF_CFLAGS)			\
 	  -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR)		\
 	  -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT)
 LDFLAGS += $(SAN_LDFLAGS)
 LDLIBS += $(LIBELF_LIBS) -lz -lrt -lpthread
 
+# The following tests perform type punning and they may break strict
+# aliasing rules, which are exploited by both GCC and clang by default
+# while optimizing.  This can lead to broken programs.
+progs/bind4_prog.c-CFLAGS := -fno-strict-aliasing
+progs/bind6_prog.c-CFLAGS := -fno-strict-aliasing
+progs/dynptr_fail.c-CFLAGS := -fno-strict-aliasing
+progs/linked_list_fail.c-CFLAGS := -fno-strict-aliasing
+progs/map_kptr_fail.c-CFLAGS := -fno-strict-aliasing
+progs/syscall.c-CFLAGS := -fno-strict-aliasing
+progs/test_pkt_md_access.c-CFLAGS := -fno-strict-aliasing
+progs/test_sk_lookup.c-CFLAGS := -fno-strict-aliasing
+progs/timer_crash.c-CFLAGS := -fno-strict-aliasing
+
 ifneq ($(LLVM),)
 # Silence some warnings when compiled with clang
 CFLAGS += -Wno-unused-command-line-argument
@@ -64,6 +77,15 @@ TEST_INST_SUBDIRS := no_alu32
 ifneq ($(BPF_GCC),)
 TEST_GEN_PROGS += test_progs-bpf_gcc
 TEST_INST_SUBDIRS += bpf_gcc
+
+# The following tests contain C code that, although technically legal,
+# triggers GCC warnings that cannot be disabled: declaration of
+# anonymous struct types in function parameter lists.
+progs/btf_dump_test_case_bitfields.c-CFLAGS := -Wno-error
+progs/btf_dump_test_case_namespacing.c-CFLAGS := -Wno-error
+progs/btf_dump_test_case_packing.c-CFLAGS := -Wno-error
+progs/btf_dump_test_case_padding.c-CFLAGS := -Wno-error
+progs/btf_dump_test_case_syntax.c-CFLAGS := -Wno-error
 endif
 
 ifneq ($(CLANG_CPUV4),)
@@ -110,7 +132,7 @@ TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
 	flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
 	test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \
 	xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \
-	xdp_features
+	xdp_features bpf_test_no_cfi.ko
 
 TEST_GEN_FILES += liburandom_read.so urandom_read sign-file uprobe_multi
 
@@ -175,8 +197,7 @@ endif
 # NOTE: Semicolon at the end is critical to override lib.mk's default static
 # rule for binaries.
 $(notdir $(TEST_GEN_PROGS)						\
-	 $(TEST_GEN_PROGS_EXTENDED)					\
-	 $(TEST_CUSTOM_PROGS)): %: $(OUTPUT)/% ;
+	 $(TEST_GEN_PROGS_EXTENDED)): %: $(OUTPUT)/% ;
 
 # sort removes libbpf duplicates when not cross-building
 MAKE_DIRS := $(sort $(BUILD_DIR)/libbpf $(HOST_BUILD_DIR)/libbpf	\
@@ -233,6 +254,12 @@ $(OUTPUT)/bpf_testmod.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_testmo
 	$(Q)$(MAKE) $(submake_extras) RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) -C bpf_testmod
 	$(Q)cp bpf_testmod/bpf_testmod.ko $@
 
+$(OUTPUT)/bpf_test_no_cfi.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_test_no_cfi/Makefile bpf_test_no_cfi/*.[ch])
+	$(call msg,MOD,,$@)
+	$(Q)$(RM) bpf_test_no_cfi/bpf_test_no_cfi.ko # force re-compilation
+	$(Q)$(MAKE) $(submake_extras) RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) -C bpf_test_no_cfi
+	$(Q)cp bpf_test_no_cfi/bpf_test_no_cfi.ko $@
+
 DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool
 ifneq ($(CROSS_COMPILE),)
 CROSS_BPFTOOL := $(SCRATCH_DIR)/sbin/bpftool
@@ -382,11 +409,11 @@ endif
 CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
 BPF_CFLAGS = -g -Wall -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN)	\
 	     -I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR)			\
-	     -I$(abspath $(OUTPUT)/../usr/include)
+	     -I$(abspath $(OUTPUT)/../usr/include)			\
+	     -Wno-compare-distinct-pointer-types
 # TODO: enable me -Wsign-compare
 
-CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \
-	       -Wno-compare-distinct-pointer-types
+CLANG_CFLAGS = $(CLANG_SYS_INCLUDES)
 
 $(OUTPUT)/test_l4lb_noinline.o: BPF_CFLAGS += -fno-inline
 $(OUTPUT)/test_xdp_noinline.o: BPF_CFLAGS += -fno-inline
@@ -504,7 +531,8 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.bpf.o:				\
 		     $(wildcard $(BPFDIR)/*.bpf.h)			\
 		     | $(TRUNNER_OUTPUT) $$(BPFOBJ)
 	$$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@,			\
-					  $(TRUNNER_BPF_CFLAGS))
+					  $(TRUNNER_BPF_CFLAGS)         \
+					  $$($$<-CFLAGS))
 
 $(TRUNNER_BPF_SKELS): %.skel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
@@ -514,6 +542,7 @@ $(TRUNNER_BPF_SKELS): %.skel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$(Q)diff $$(<:.o=.linked2.o) $$(<:.o=.linked3.o)
 	$(Q)$$(BPFTOOL) gen skeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.bpf.o=)) > $$@
 	$(Q)$$(BPFTOOL) gen subskeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.bpf.o=)) > $$(@:.skel.h=.subskel.h)
+	$(Q)rm -f $$(<:.o=.linked1.o) $$(<:.o=.linked2.o) $$(<:.o=.linked3.o)
 
 $(TRUNNER_BPF_LSKELS): %.lskel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
@@ -522,6 +551,7 @@ $(TRUNNER_BPF_LSKELS): %.lskel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$(Q)$$(BPFTOOL) gen object $$(<:.o=.llinked3.o) $$(<:.o=.llinked2.o)
 	$(Q)diff $$(<:.o=.llinked2.o) $$(<:.o=.llinked3.o)
 	$(Q)$$(BPFTOOL) gen skeleton -L $$(<:.o=.llinked3.o) name $$(notdir $$(<:.bpf.o=_lskel)) > $$@
+	$(Q)rm -f $$(<:.o=.llinked1.o) $$(<:.o=.llinked2.o) $$(<:.o=.llinked3.o)
 
 $(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_BPF_OBJS) $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$$(call msg,LINK-BPF,$(TRUNNER_BINARY),$$(@:.skel.h=.bpf.o))
@@ -532,6 +562,7 @@ $(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_BPF_OBJS) $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
 	$(Q)$$(BPFTOOL) gen skeleton $$(@:.skel.h=.linked3.o) name $$(notdir $$(@:.skel.h=)) > $$@
 	$(Q)$$(BPFTOOL) gen subskeleton $$(@:.skel.h=.linked3.o) name $$(notdir $$(@:.skel.h=)) > $$(@:.skel.h=.subskel.h)
+	$(Q)rm -f $$(@:.skel.h=.linked1.o) $$(@:.skel.h=.linked2.o) $$(@:.skel.h=.linked3.o)
 endif
 
 # ensure we set up tests.h header generation rule just once
@@ -606,6 +637,7 @@ TRUNNER_EXTRA_SOURCES := test_progs.c		\
 			 flow_dissector_load.h	\
 			 ip_check_defrag_frags.h
 TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko	\
+		       $(OUTPUT)/bpf_test_no_cfi.ko			\
 		       $(OUTPUT)/liburandom_read.so			\
 		       $(OUTPUT)/xdp_synproxy				\
 		       $(OUTPUT)/sign-file				\
@@ -729,11 +761,12 @@ $(OUTPUT)/uprobe_multi: uprobe_multi.c
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $^ $(LDLIBS) -o $@
 
-EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR)	\
+EXTRA_CLEAN := $(SCRATCH_DIR) $(HOST_SCRATCH_DIR)			\
 	prog_tests/tests.h map_tests/tests.h verifier/tests.h		\
 	feature bpftool							\
 	$(addprefix $(OUTPUT)/,*.o *.skel.h *.lskel.h *.subskel.h	\
 			       no_alu32 cpuv4 bpf_gcc bpf_testmod.ko	\
+			       bpf_test_no_cfi.ko			\
 			       liburandom_read.so)
 
 .PHONY: docs docs-clean
diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index 9af79c7a9b..9b974e425a 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -115,7 +115,7 @@ the insn 20 undoes map_value addition. It is currently impossible for the
 verifier to understand such speculative pointer arithmetic.
 Hence `this patch`__ addresses it on the compiler side. It was committed on llvm 12.
 
-__ https://reviews.llvm.org/D85570
+__ https://github.com/llvm/llvm-project/commit/ddf1864ace484035e3cde5e83b3a31ac81e059c6
 
 The corresponding C code
 
@@ -165,7 +165,7 @@ This is due to a llvm BPF backend bug. `The fix`__
 has been pushed to llvm 10.x release branch and will be
 available in 10.0.1. The patch is available in llvm 11.0.0 trunk.
 
-__  https://reviews.llvm.org/D78466
+__  https://github.com/llvm/llvm-project/commit/3cb7e7bf959dcd3b8080986c62e10a75c7af43f0
 
 bpf_verif_scale/loop6.bpf.o test failure with Clang 12
 ======================================================
@@ -204,7 +204,7 @@ r5(w5) is eventually saved on stack at insn #24 for later use.
 This cause later verifier failure. The bug has been `fixed`__ in
 Clang 13.
 
-__  https://reviews.llvm.org/D97479
+__  https://github.com/llvm/llvm-project/commit/1959ead525b8830cc8a345f45e1c3ef9902d3229
 
 BPF CO-RE-based tests and Clang version
 =======================================
@@ -221,11 +221,11 @@ failures:
 - __builtin_btf_type_id() [0_, 1_, 2_];
 - __builtin_preserve_type_info(), __builtin_preserve_enum_value() [3_, 4_].
 
-.. _0: https://reviews.llvm.org/D74572
-.. _1: https://reviews.llvm.org/D74668
-.. _2: https://reviews.llvm.org/D85174
-.. _3: https://reviews.llvm.org/D83878
-.. _4: https://reviews.llvm.org/D83242
+.. _0: https://github.com/llvm/llvm-project/commit/6b01b465388b204d543da3cf49efd6080db094a9
+.. _1: https://github.com/llvm/llvm-project/commit/072cde03aaa13a2c57acf62d79876bf79aa1919f
+.. _2: https://github.com/llvm/llvm-project/commit/00602ee7ef0bf6c68d690a2bd729c12b95c95c99
+.. _3: https://github.com/llvm/llvm-project/commit/6d218b4adb093ff2e9764febbbc89f429412006c
+.. _4: https://github.com/llvm/llvm-project/commit/6d6750696400e7ce988d66a1a00e1d0cb32815f8
 
 Floating-point tests and Clang version
 ======================================
@@ -234,7 +234,7 @@ Certain selftests, e.g. core_reloc, require support for the floating-point
 types, which was introduced in `Clang 13`__. The older Clang versions will
 either crash when compiling these tests, or generate an incorrect BTF.
 
-__  https://reviews.llvm.org/D83289
+__  https://github.com/llvm/llvm-project/commit/a7137b238a07d9399d3ae96c0b461571bd5aa8b2
 
 Kernel function call test and Clang version
 ===========================================
@@ -248,7 +248,7 @@ Without it, the error from compiling bpf selftests looks like:
 
   libbpf: failed to find BTF for extern 'tcp_slow_start' [25] section: -2
 
-__ https://reviews.llvm.org/D93563
+__ https://github.com/llvm/llvm-project/commit/886f9ff53155075bd5f1e994f17b85d1e1b7470c
 
 btf_tag test and Clang version
 ==============================
@@ -264,8 +264,8 @@ Without them, the btf_tag selftest will be skipped and you will observe:
 
   #<test_num> btf_tag:SKIP
 
-.. _0: https://reviews.llvm.org/D111588
-.. _1: https://reviews.llvm.org/D111199
+.. _0: https://github.com/llvm/llvm-project/commit/a162b67c98066218d0d00aa13b99afb95d9bb5e6
+.. _1: https://github.com/llvm/llvm-project/commit/3466e00716e12e32fdb100e3fcfca5c2b3e8d784
 
 Clang dependencies for static linking tests
 ===========================================
@@ -274,7 +274,7 @@ linked_vars, linked_maps, and linked_funcs tests depend on `Clang fix`__ to
 generate valid BTF information for weak variables. Please make sure you use
 Clang that contains the fix.
 
-__ https://reviews.llvm.org/D100362
+__ https://github.com/llvm/llvm-project/commit/968292cb93198442138128d850fd54dc7edc0035
 
 Clang relocation changes
 ========================
@@ -292,7 +292,7 @@ Here, ``type 2`` refers to new relocation type ``R_BPF_64_ABS64``.
 To fix this issue, user newer libbpf.
 
 .. Links
-.. _clang reloc patch: https://reviews.llvm.org/D102712
+.. _clang reloc patch: https://github.com/llvm/llvm-project/commit/6a2ea84600ba4bd3b2733bd8f08f5115eb32164b
 .. _kernel llvm reloc: /Documentation/bpf/llvm_reloc.rst
 
 Clang dependencies for the u32 spill test (xdpwall)
@@ -304,6 +304,6 @@ from running test_progs will look like:
 
 .. code-block:: console
 
-  test_xdpwall:FAIL:Does LLVM have https://reviews.llvm.org/D109073? unexpected error: -4007
+  test_xdpwall:FAIL:Does LLVM have https://github.com/llvm/llvm-project/commit/ea72b0319d7b0f0c2fcf41d121afa5d031b319d5? unexpected error: -4007
 
-__ https://reviews.llvm.org/D109073
+__ https://github.com/llvm/llvm-project/commit/ea72b0319d7b0f0c2fcf41d121afa5d031b319d5
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index 73ce11b054..b2b4c391eb 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -323,14 +323,14 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 		break;
 	case 'p':
 		env.producer_cnt = strtol(arg, NULL, 10);
-		if (env.producer_cnt <= 0) {
+		if (env.producer_cnt < 0) {
 			fprintf(stderr, "Invalid producer count: %s\n", arg);
 			argp_usage(state);
 		}
 		break;
 	case 'c':
 		env.consumer_cnt = strtol(arg, NULL, 10);
-		if (env.consumer_cnt <= 0) {
+		if (env.consumer_cnt < 0) {
 			fprintf(stderr, "Invalid consumer count: %s\n", arg);
 			argp_usage(state);
 		}
@@ -495,14 +495,20 @@ extern const struct bench bench_trig_base;
 extern const struct bench bench_trig_tp;
 extern const struct bench bench_trig_rawtp;
 extern const struct bench bench_trig_kprobe;
+extern const struct bench bench_trig_kretprobe;
+extern const struct bench bench_trig_kprobe_multi;
+extern const struct bench bench_trig_kretprobe_multi;
 extern const struct bench bench_trig_fentry;
+extern const struct bench bench_trig_fexit;
 extern const struct bench bench_trig_fentry_sleep;
 extern const struct bench bench_trig_fmodret;
 extern const struct bench bench_trig_uprobe_base;
-extern const struct bench bench_trig_uprobe_with_nop;
-extern const struct bench bench_trig_uretprobe_with_nop;
-extern const struct bench bench_trig_uprobe_without_nop;
-extern const struct bench bench_trig_uretprobe_without_nop;
+extern const struct bench bench_trig_uprobe_nop;
+extern const struct bench bench_trig_uretprobe_nop;
+extern const struct bench bench_trig_uprobe_push;
+extern const struct bench bench_trig_uretprobe_push;
+extern const struct bench bench_trig_uprobe_ret;
+extern const struct bench bench_trig_uretprobe_ret;
 extern const struct bench bench_rb_libbpf;
 extern const struct bench bench_rb_custom;
 extern const struct bench bench_pb_libbpf;
@@ -537,14 +543,20 @@ static const struct bench *benchs[] = {
 	&bench_trig_tp,
 	&bench_trig_rawtp,
 	&bench_trig_kprobe,
+	&bench_trig_kretprobe,
+	&bench_trig_kprobe_multi,
+	&bench_trig_kretprobe_multi,
 	&bench_trig_fentry,
+	&bench_trig_fexit,
 	&bench_trig_fentry_sleep,
 	&bench_trig_fmodret,
 	&bench_trig_uprobe_base,
-	&bench_trig_uprobe_with_nop,
-	&bench_trig_uretprobe_with_nop,
-	&bench_trig_uprobe_without_nop,
-	&bench_trig_uretprobe_without_nop,
+	&bench_trig_uprobe_nop,
+	&bench_trig_uretprobe_nop,
+	&bench_trig_uprobe_push,
+	&bench_trig_uretprobe_push,
+	&bench_trig_uprobe_ret,
+	&bench_trig_uretprobe_ret,
 	&bench_rb_libbpf,
 	&bench_rb_custom,
 	&bench_pb_libbpf,
@@ -607,6 +619,10 @@ static void setup_benchmark(void)
 		bench->setup();
 
 	for (i = 0; i < env.consumer_cnt; i++) {
+		if (!bench->consumer_thread) {
+			fprintf(stderr, "benchmark doesn't support consumers!\n");
+			exit(1);
+		}
 		err = pthread_create(&state.consumers[i], NULL,
 				     bench->consumer_thread, (void *)(long)i);
 		if (err) {
@@ -626,6 +642,10 @@ static void setup_benchmark(void)
 		env.prod_cpus.next_cpu = env.cons_cpus.next_cpu;
 
 	for (i = 0; i < env.producer_cnt; i++) {
+		if (!bench->producer_thread) {
+			fprintf(stderr, "benchmark doesn't support producers!\n");
+			exit(1);
+		}
 		err = pthread_create(&state.producers[i], NULL,
 				     bench->producer_thread, (void *)(long)i);
 		if (err) {
diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
index dbd362771d..ace0d1011a 100644
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -85,12 +85,36 @@ static void trigger_kprobe_setup(void)
 	attach_bpf(ctx.skel->progs.bench_trigger_kprobe);
 }
 
+static void trigger_kretprobe_setup(void)
+{
+	setup_ctx();
+	attach_bpf(ctx.skel->progs.bench_trigger_kretprobe);
+}
+
+static void trigger_kprobe_multi_setup(void)
+{
+	setup_ctx();
+	attach_bpf(ctx.skel->progs.bench_trigger_kprobe_multi);
+}
+
+static void trigger_kretprobe_multi_setup(void)
+{
+	setup_ctx();
+	attach_bpf(ctx.skel->progs.bench_trigger_kretprobe_multi);
+}
+
 static void trigger_fentry_setup(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.bench_trigger_fentry);
 }
 
+static void trigger_fexit_setup(void)
+{
+	setup_ctx();
+	attach_bpf(ctx.skel->progs.bench_trigger_fexit);
+}
+
 static void trigger_fentry_sleep_setup(void)
 {
 	setup_ctx();
@@ -113,12 +137,25 @@ static void trigger_fmodret_setup(void)
  * GCC doesn't generate stack setup preample for these functions due to them
  * having no input arguments and doing nothing in the body.
  */
-__weak void uprobe_target_with_nop(void)
+__weak void uprobe_target_nop(void)
 {
 	asm volatile ("nop");
 }
 
-__weak void uprobe_target_without_nop(void)
+__weak void opaque_noop_func(void)
+{
+}
+
+__weak int uprobe_target_push(void)
+{
+	/* overhead of function call is negligible compared to uprobe
+	 * triggering, so this shouldn't affect benchmark results much
+	 */
+	opaque_noop_func();
+	return 1;
+}
+
+__weak void uprobe_target_ret(void)
 {
 	asm volatile ("");
 }
@@ -126,27 +163,34 @@ __weak void uprobe_target_without_nop(void)
 static void *uprobe_base_producer(void *input)
 {
 	while (true) {
-		uprobe_target_with_nop();
+		uprobe_target_nop();
 		atomic_inc(&base_hits.value);
 	}
 	return NULL;
 }
 
-static void *uprobe_producer_with_nop(void *input)
+static void *uprobe_producer_nop(void *input)
+{
+	while (true)
+		uprobe_target_nop();
+	return NULL;
+}
+
+static void *uprobe_producer_push(void *input)
 {
 	while (true)
-		uprobe_target_with_nop();
+		uprobe_target_push();
 	return NULL;
 }
 
-static void *uprobe_producer_without_nop(void *input)
+static void *uprobe_producer_ret(void *input)
 {
 	while (true)
-		uprobe_target_without_nop();
+		uprobe_target_ret();
 	return NULL;
 }
 
-static void usetup(bool use_retprobe, bool use_nop)
+static void usetup(bool use_retprobe, void *target_addr)
 {
 	size_t uprobe_offset;
 	struct bpf_link *link;
@@ -159,11 +203,7 @@ static void usetup(bool use_retprobe, bool use_nop)
 		exit(1);
 	}
 
-	if (use_nop)
-		uprobe_offset = get_uprobe_offset(&uprobe_target_with_nop);
-	else
-		uprobe_offset = get_uprobe_offset(&uprobe_target_without_nop);
-
+	uprobe_offset = get_uprobe_offset(target_addr);
 	link = bpf_program__attach_uprobe(ctx.skel->progs.bench_trigger_uprobe,
 					  use_retprobe,
 					  -1 /* all PIDs */,
@@ -176,24 +216,34 @@ static void usetup(bool use_retprobe, bool use_nop)
 	ctx.skel->links.bench_trigger_uprobe = link;
 }
 
-static void uprobe_setup_with_nop(void)
+static void uprobe_setup_nop(void)
 {
-	usetup(false, true);
+	usetup(false, &uprobe_target_nop);
 }
 
-static void uretprobe_setup_with_nop(void)
+static void uretprobe_setup_nop(void)
 {
-	usetup(true, true);
+	usetup(true, &uprobe_target_nop);
 }
 
-static void uprobe_setup_without_nop(void)
+static void uprobe_setup_push(void)
 {
-	usetup(false, false);
+	usetup(false, &uprobe_target_push);
 }
 
-static void uretprobe_setup_without_nop(void)
+static void uretprobe_setup_push(void)
 {
-	usetup(true, false);
+	usetup(true, &uprobe_target_push);
+}
+
+static void uprobe_setup_ret(void)
+{
+	usetup(false, &uprobe_target_ret);
+}
+
+static void uretprobe_setup_ret(void)
+{
+	usetup(true, &uprobe_target_ret);
 }
 
 const struct bench bench_trig_base = {
@@ -235,6 +285,36 @@ const struct bench bench_trig_kprobe = {
 	.report_final = hits_drops_report_final,
 };
 
+const struct bench bench_trig_kretprobe = {
+	.name = "trig-kretprobe",
+	.validate = trigger_validate,
+	.setup = trigger_kretprobe_setup,
+	.producer_thread = trigger_producer,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_kprobe_multi = {
+	.name = "trig-kprobe-multi",
+	.validate = trigger_validate,
+	.setup = trigger_kprobe_multi_setup,
+	.producer_thread = trigger_producer,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_kretprobe_multi = {
+	.name = "trig-kretprobe-multi",
+	.validate = trigger_validate,
+	.setup = trigger_kretprobe_multi_setup,
+	.producer_thread = trigger_producer,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
 const struct bench bench_trig_fentry = {
 	.name = "trig-fentry",
 	.validate = trigger_validate,
@@ -245,6 +325,16 @@ const struct bench bench_trig_fentry = {
 	.report_final = hits_drops_report_final,
 };
 
+const struct bench bench_trig_fexit = {
+	.name = "trig-fexit",
+	.validate = trigger_validate,
+	.setup = trigger_fexit_setup,
+	.producer_thread = trigger_producer,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
 const struct bench bench_trig_fentry_sleep = {
 	.name = "trig-fentry-sleep",
 	.validate = trigger_validate,
@@ -274,37 +364,55 @@ const struct bench bench_trig_uprobe_base = {
 	.report_final = hits_drops_report_final,
 };
 
-const struct bench bench_trig_uprobe_with_nop = {
-	.name = "trig-uprobe-with-nop",
-	.setup = uprobe_setup_with_nop,
-	.producer_thread = uprobe_producer_with_nop,
+const struct bench bench_trig_uprobe_nop = {
+	.name = "trig-uprobe-nop",
+	.setup = uprobe_setup_nop,
+	.producer_thread = uprobe_producer_nop,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_uretprobe_nop = {
+	.name = "trig-uretprobe-nop",
+	.setup = uretprobe_setup_nop,
+	.producer_thread = uprobe_producer_nop,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_uprobe_push = {
+	.name = "trig-uprobe-push",
+	.setup = uprobe_setup_push,
+	.producer_thread = uprobe_producer_push,
 	.measure = trigger_measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
 };
 
-const struct bench bench_trig_uretprobe_with_nop = {
-	.name = "trig-uretprobe-with-nop",
-	.setup = uretprobe_setup_with_nop,
-	.producer_thread = uprobe_producer_with_nop,
+const struct bench bench_trig_uretprobe_push = {
+	.name = "trig-uretprobe-push",
+	.setup = uretprobe_setup_push,
+	.producer_thread = uprobe_producer_push,
 	.measure = trigger_measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
 };
 
-const struct bench bench_trig_uprobe_without_nop = {
-	.name = "trig-uprobe-without-nop",
-	.setup = uprobe_setup_without_nop,
-	.producer_thread = uprobe_producer_without_nop,
+const struct bench bench_trig_uprobe_ret = {
+	.name = "trig-uprobe-ret",
+	.setup = uprobe_setup_ret,
+	.producer_thread = uprobe_producer_ret,
 	.measure = trigger_measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
 };
 
-const struct bench bench_trig_uretprobe_without_nop = {
-	.name = "trig-uretprobe-without-nop",
-	.setup = uretprobe_setup_without_nop,
-	.producer_thread = uprobe_producer_without_nop,
+const struct bench bench_trig_uretprobe_ret = {
+	.name = "trig-uretprobe-ret",
+	.setup = uretprobe_setup_ret,
+	.producer_thread = uprobe_producer_ret,
 	.measure = trigger_measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh b/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh
new file mode 100755
index 0000000000..9bdcc74e03
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+
+set -eufo pipefail
+
+for i in base {uprobe,uretprobe}-{nop,push,ret}
+do
+	summary=$(sudo ./bench -w2 -d5 -a trig-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
+	printf "%-15s: %s\n" $i "$summary"
+done
diff --git a/tools/testing/selftests/bpf/bpf_arena_alloc.h b/tools/testing/selftests/bpf/bpf_arena_alloc.h
new file mode 100644
index 0000000000..c27678299e
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_arena_alloc.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#pragma once
+#include "bpf_arena_common.h"
+
+#ifndef __round_mask
+#define __round_mask(x, y) ((__typeof__(x))((y)-1))
+#endif
+#ifndef round_up
+#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
+#endif
+
+#ifdef __BPF__
+#define NR_CPUS (sizeof(struct cpumask) * 8)
+
+static void __arena * __arena page_frag_cur_page[NR_CPUS];
+static int __arena page_frag_cur_offset[NR_CPUS];
+
+/* Simple page_frag allocator */
+static inline void __arena* bpf_alloc(unsigned int size)
+{
+	__u64 __arena *obj_cnt;
+	__u32 cpu = bpf_get_smp_processor_id();
+	void __arena *page = page_frag_cur_page[cpu];
+	int __arena *cur_offset = &page_frag_cur_offset[cpu];
+	int offset;
+
+	size = round_up(size, 8);
+	if (size >= PAGE_SIZE - 8)
+		return NULL;
+	if (!page) {
+refill:
+		page = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+		if (!page)
+			return NULL;
+		cast_kern(page);
+		page_frag_cur_page[cpu] = page;
+		*cur_offset = PAGE_SIZE - 8;
+		obj_cnt = page + PAGE_SIZE - 8;
+		*obj_cnt = 0;
+	} else {
+		cast_kern(page);
+		obj_cnt = page + PAGE_SIZE - 8;
+	}
+
+	offset = *cur_offset - size;
+	if (offset < 0)
+		goto refill;
+
+	(*obj_cnt)++;
+	*cur_offset = offset;
+	return page + offset;
+}
+
+static inline void bpf_free(void __arena *addr)
+{
+	__u64 __arena *obj_cnt;
+
+	addr = (void __arena *)(((long)addr) & ~(PAGE_SIZE - 1));
+	obj_cnt = addr + PAGE_SIZE - 8;
+	if (--(*obj_cnt) == 0)
+		bpf_arena_free_pages(&arena, addr, 1);
+}
+#else
+static inline void __arena* bpf_alloc(unsigned int size) { return NULL; }
+static inline void bpf_free(void __arena *addr) {}
+#endif
diff --git a/tools/testing/selftests/bpf/bpf_arena_common.h b/tools/testing/selftests/bpf/bpf_arena_common.h
new file mode 100644
index 0000000000..567491f3e1
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_arena_common.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#pragma once
+
+#ifndef WRITE_ONCE
+#define WRITE_ONCE(x, val) ((*(volatile typeof(x) *) &(x)) = (val))
+#endif
+
+#ifndef NUMA_NO_NODE
+#define	NUMA_NO_NODE	(-1)
+#endif
+
+#ifndef arena_container_of
+#define arena_container_of(ptr, type, member)			\
+	({							\
+		void __arena *__mptr = (void __arena *)(ptr);	\
+		((type *)(__mptr - offsetof(type, member)));	\
+	})
+#endif
+
+#ifdef __BPF__ /* when compiled as bpf program */
+
+#ifndef PAGE_SIZE
+#define PAGE_SIZE __PAGE_SIZE
+/*
+ * for older kernels try sizeof(struct genradix_node)
+ * or flexible:
+ * static inline long __bpf_page_size(void) {
+ *   return bpf_core_enum_value(enum page_size_enum___l, __PAGE_SIZE___l) ?: sizeof(struct genradix_node);
+ * }
+ * but generated code is not great.
+ */
+#endif
+
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST) && !defined(BPF_ARENA_FORCE_ASM)
+#define __arena __attribute__((address_space(1)))
+#define cast_kern(ptr) /* nop for bpf prog. emitted by LLVM */
+#define cast_user(ptr) /* nop for bpf prog. emitted by LLVM */
+#else
+#define __arena
+#define cast_kern(ptr) bpf_addr_space_cast(ptr, 0, 1)
+#define cast_user(ptr) bpf_addr_space_cast(ptr, 1, 0)
+#endif
+
+void __arena* bpf_arena_alloc_pages(void *map, void __arena *addr, __u32 page_cnt,
+				    int node_id, __u64 flags) __ksym __weak;
+void bpf_arena_free_pages(void *map, void __arena *ptr, __u32 page_cnt) __ksym __weak;
+
+#else /* when compiled as user space code */
+
+#define __arena
+#define __arg_arena
+#define cast_kern(ptr) /* nop for user space */
+#define cast_user(ptr) /* nop for user space */
+__weak char arena[1];
+
+#ifndef offsetof
+#define offsetof(type, member)  ((unsigned long)&((type *)0)->member)
+#endif
+
+static inline void __arena* bpf_arena_alloc_pages(void *map, void *addr, __u32 page_cnt,
+						  int node_id, __u64 flags)
+{
+	return NULL;
+}
+static inline void bpf_arena_free_pages(void *map, void __arena *ptr, __u32 page_cnt)
+{
+}
+
+#endif
diff --git a/tools/testing/selftests/bpf/bpf_arena_htab.h b/tools/testing/selftests/bpf/bpf_arena_htab.h
new file mode 100644
index 0000000000..acc01a8766
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_arena_htab.h
@@ -0,0 +1,100 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#pragma once
+#include <errno.h>
+#include "bpf_arena_alloc.h"
+#include "bpf_arena_list.h"
+
+struct htab_bucket {
+	struct arena_list_head head;
+};
+typedef struct htab_bucket __arena htab_bucket_t;
+
+struct htab {
+	htab_bucket_t *buckets;
+	int n_buckets;
+};
+typedef struct htab __arena htab_t;
+
+static inline htab_bucket_t *__select_bucket(htab_t *htab, __u32 hash)
+{
+	htab_bucket_t *b = htab->buckets;
+
+	cast_kern(b);
+	return &b[hash & (htab->n_buckets - 1)];
+}
+
+static inline arena_list_head_t *select_bucket(htab_t *htab, __u32 hash)
+{
+	return &__select_bucket(htab, hash)->head;
+}
+
+struct hashtab_elem {
+	int hash;
+	int key;
+	int value;
+	struct arena_list_node hash_node;
+};
+typedef struct hashtab_elem __arena hashtab_elem_t;
+
+static hashtab_elem_t *lookup_elem_raw(arena_list_head_t *head, __u32 hash, int key)
+{
+	hashtab_elem_t *l;
+
+	list_for_each_entry(l, head, hash_node)
+		if (l->hash == hash && l->key == key)
+			return l;
+
+	return NULL;
+}
+
+static int htab_hash(int key)
+{
+	return key;
+}
+
+__weak int htab_lookup_elem(htab_t *htab __arg_arena, int key)
+{
+	hashtab_elem_t *l_old;
+	arena_list_head_t *head;
+
+	cast_kern(htab);
+	head = select_bucket(htab, key);
+	l_old = lookup_elem_raw(head, htab_hash(key), key);
+	if (l_old)
+		return l_old->value;
+	return 0;
+}
+
+__weak int htab_update_elem(htab_t *htab __arg_arena, int key, int value)
+{
+	hashtab_elem_t *l_new = NULL, *l_old;
+	arena_list_head_t *head;
+
+	cast_kern(htab);
+	head = select_bucket(htab, key);
+	l_old = lookup_elem_raw(head, htab_hash(key), key);
+
+	l_new = bpf_alloc(sizeof(*l_new));
+	if (!l_new)
+		return -ENOMEM;
+	l_new->key = key;
+	l_new->hash = htab_hash(key);
+	l_new->value = value;
+
+	list_add_head(&l_new->hash_node, head);
+	if (l_old) {
+		list_del(&l_old->hash_node);
+		bpf_free(l_old);
+	}
+	return 0;
+}
+
+void htab_init(htab_t *htab)
+{
+	void __arena *buckets = bpf_arena_alloc_pages(&arena, NULL, 2, NUMA_NO_NODE, 0);
+
+	cast_user(buckets);
+	htab->buckets = buckets;
+	htab->n_buckets = 2 * PAGE_SIZE / sizeof(struct htab_bucket);
+}
diff --git a/tools/testing/selftests/bpf/bpf_arena_list.h b/tools/testing/selftests/bpf/bpf_arena_list.h
new file mode 100644
index 0000000000..b99b9f408e
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_arena_list.h
@@ -0,0 +1,92 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#pragma once
+#include "bpf_arena_common.h"
+
+struct arena_list_node;
+
+typedef struct arena_list_node __arena arena_list_node_t;
+
+struct arena_list_node {
+	arena_list_node_t *next;
+	arena_list_node_t * __arena *pprev;
+};
+
+struct arena_list_head {
+	struct arena_list_node __arena *first;
+};
+typedef struct arena_list_head __arena arena_list_head_t;
+
+#define list_entry(ptr, type, member) arena_container_of(ptr, type, member)
+
+#define list_entry_safe(ptr, type, member) \
+	({ typeof(*ptr) * ___ptr = (ptr); \
+	 ___ptr ? ({ cast_kern(___ptr); list_entry(___ptr, type, member); }) : NULL; \
+	 })
+
+#ifndef __BPF__
+static inline void *bpf_iter_num_new(struct bpf_iter_num *it, int i, int j) { return NULL; }
+static inline void bpf_iter_num_destroy(struct bpf_iter_num *it) {}
+static inline bool bpf_iter_num_next(struct bpf_iter_num *it) { return true; }
+#define cond_break ({})
+#endif
+
+/* Safely walk link list elements. Deletion of elements is allowed. */
+#define list_for_each_entry(pos, head, member)					\
+	for (void * ___tmp = (pos = list_entry_safe((head)->first,		\
+						    typeof(*(pos)), member),	\
+			      (void *)0);					\
+	     pos && ({ ___tmp = (void *)pos->member.next; 1; });		\
+	     cond_break,							\
+	     pos = list_entry_safe((void __arena *)___tmp, typeof(*(pos)), member))
+
+static inline void list_add_head(arena_list_node_t *n, arena_list_head_t *h)
+{
+	arena_list_node_t *first = h->first, * __arena *tmp;
+
+	cast_user(first);
+	cast_kern(n);
+	WRITE_ONCE(n->next, first);
+	cast_kern(first);
+	if (first) {
+		tmp = &n->next;
+		cast_user(tmp);
+		WRITE_ONCE(first->pprev, tmp);
+	}
+	cast_user(n);
+	WRITE_ONCE(h->first, n);
+
+	tmp = &h->first;
+	cast_user(tmp);
+	cast_kern(n);
+	WRITE_ONCE(n->pprev, tmp);
+}
+
+static inline void __list_del(arena_list_node_t *n)
+{
+	arena_list_node_t *next = n->next, *tmp;
+	arena_list_node_t * __arena *pprev = n->pprev;
+
+	cast_user(next);
+	cast_kern(pprev);
+	tmp = *pprev;
+	cast_kern(tmp);
+	WRITE_ONCE(tmp, next);
+	if (next) {
+		cast_user(pprev);
+		cast_kern(next);
+		WRITE_ONCE(next->pprev, pprev);
+	}
+}
+
+#define POISON_POINTER_DELTA 0
+
+#define LIST_POISON1  ((void __arena *) 0x100 + POISON_POINTER_DELTA)
+#define LIST_POISON2  ((void __arena *) 0x122 + POISON_POINTER_DELTA)
+
+static inline void list_del(arena_list_node_t *n)
+{
+	__list_del(n);
+	n->next = LIST_POISON1;
+	n->pprev = LIST_POISON2;
+}
diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index f44875f8b3..a5b9df38c1 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -260,11 +260,11 @@ extern void bpf_throw(u64 cookie) __ksym;
 
 #define __is_signed_type(type) (((type)(-1)) < (type)1)
 
-#define __bpf_cmp(LHS, OP, SIGN, PRED, RHS, DEFAULT)						\
+#define __bpf_cmp(LHS, OP, PRED, RHS, DEFAULT)						\
 	({											\
 		__label__ l_true;								\
 		bool ret = DEFAULT;								\
-		asm volatile goto("if %[lhs] " SIGN #OP " %[rhs] goto %l[l_true]"		\
+		asm volatile goto("if %[lhs] " OP " %[rhs] goto %l[l_true]"		\
 				  :: [lhs] "r"((short)LHS), [rhs] PRED (RHS) :: l_true);	\
 		ret = !DEFAULT;									\
 l_true:												\
@@ -276,7 +276,7 @@ l_true:												\
  * __lhs OP __rhs below will catch the mistake.
  * Be aware that we check only __lhs to figure out the sign of compare.
  */
-#define _bpf_cmp(LHS, OP, RHS, NOFLIP)								\
+#define _bpf_cmp(LHS, OP, RHS, UNLIKELY)								\
 	({											\
 		typeof(LHS) __lhs = (LHS);							\
 		typeof(RHS) __rhs = (RHS);							\
@@ -285,14 +285,17 @@ l_true:												\
 		(void)(__lhs OP __rhs);								\
 		if (__cmp_cannot_be_signed(OP) || !__is_signed_type(typeof(__lhs))) {		\
 			if (sizeof(__rhs) == 8)							\
-				ret = __bpf_cmp(__lhs, OP, "", "r", __rhs, NOFLIP);		\
+				/* "i" will truncate 64-bit constant into s32,			\
+				 * so we have to use extra register via "r".			\
+				 */								\
+				ret = __bpf_cmp(__lhs, #OP, "r", __rhs, UNLIKELY);		\
 			else									\
-				ret = __bpf_cmp(__lhs, OP, "", "i", __rhs, NOFLIP);		\
+				ret = __bpf_cmp(__lhs, #OP, "ri", __rhs, UNLIKELY);		\
 		} else {									\
 			if (sizeof(__rhs) == 8)							\
-				ret = __bpf_cmp(__lhs, OP, "s", "r", __rhs, NOFLIP);		\
+				ret = __bpf_cmp(__lhs, "s"#OP, "r", __rhs, UNLIKELY);		\
 			else									\
-				ret = __bpf_cmp(__lhs, OP, "s", "i", __rhs, NOFLIP);		\
+				ret = __bpf_cmp(__lhs, "s"#OP, "ri", __rhs, UNLIKELY);		\
 		}										\
 		ret;										\
        })
@@ -304,7 +307,7 @@ l_true:												\
 #ifndef bpf_cmp_likely
 #define bpf_cmp_likely(LHS, OP, RHS)								\
 	({											\
-		bool ret;									\
+		bool ret = 0;									\
 		if (__builtin_strcmp(#OP, "==") == 0)						\
 			ret = _bpf_cmp(LHS, !=, RHS, false);					\
 		else if (__builtin_strcmp(#OP, "!=") == 0)					\
@@ -318,16 +321,71 @@ l_true:												\
 		else if (__builtin_strcmp(#OP, ">=") == 0)					\
 			ret = _bpf_cmp(LHS, <, RHS, false);					\
 		else										\
-			(void) "bug";								\
+			asm volatile("r0 " #OP " invalid compare");				\
 		ret;										\
        })
 #endif
 
+#define cond_break					\
+	({ __label__ l_break, l_continue;		\
+	 asm volatile goto("1:.byte 0xe5;			\
+		      .byte 0;				\
+		      .long ((%l[l_break] - 1b - 8) / 8) & 0xffff;	\
+		      .short 0"				\
+		      :::: l_break);			\
+	goto l_continue;				\
+	l_break: break;					\
+	l_continue:;					\
+	})
+
 #ifndef bpf_nop_mov
 #define bpf_nop_mov(var) \
 	asm volatile("%[reg]=%[reg]"::[reg]"r"((short)var))
 #endif
 
+/* emit instruction:
+ * rX = rX .off = BPF_ADDR_SPACE_CAST .imm32 = (dst_as << 16) | src_as
+ */
+#ifndef bpf_addr_space_cast
+#define bpf_addr_space_cast(var, dst_as, src_as)\
+	asm volatile(".byte 0xBF;		\
+		     .ifc %[reg], r0;		\
+		     .byte 0x00;		\
+		     .endif;			\
+		     .ifc %[reg], r1;		\
+		     .byte 0x11;		\
+		     .endif;			\
+		     .ifc %[reg], r2;		\
+		     .byte 0x22;		\
+		     .endif;			\
+		     .ifc %[reg], r3;		\
+		     .byte 0x33;		\
+		     .endif;			\
+		     .ifc %[reg], r4;		\
+		     .byte 0x44;		\
+		     .endif;			\
+		     .ifc %[reg], r5;		\
+		     .byte 0x55;		\
+		     .endif;			\
+		     .ifc %[reg], r6;		\
+		     .byte 0x66;		\
+		     .endif;			\
+		     .ifc %[reg], r7;		\
+		     .byte 0x77;		\
+		     .endif;			\
+		     .ifc %[reg], r8;		\
+		     .byte 0x88;		\
+		     .endif;			\
+		     .ifc %[reg], r9;		\
+		     .byte 0x99;		\
+		     .endif;			\
+		     .short %[off];		\
+		     .long %[as]"		\
+		     : [reg]"+r"(var)		\
+		     : [off]"i"(BPF_ADDR_SPACE_CAST) \
+		     , [as]"i"((dst_as << 16) | src_as));
+#endif
+
 /* Description
  *	Assert that a conditional expression is true.
  * Returns
diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h
index b4e78c1eb3..14ebe7d9e1 100644
--- a/tools/testing/selftests/bpf/bpf_kfuncs.h
+++ b/tools/testing/selftests/bpf/bpf_kfuncs.h
@@ -9,7 +9,7 @@ struct bpf_sock_addr_kern;
  *  Error code
  */
 extern int bpf_dynptr_from_skb(struct __sk_buff *skb, __u64 flags,
-    struct bpf_dynptr *ptr__uninit) __ksym;
+    struct bpf_dynptr *ptr__uninit) __ksym __weak;
 
 /* Description
  *  Initializes an xdp-type dynptr
@@ -17,7 +17,7 @@ extern int bpf_dynptr_from_skb(struct __sk_buff *skb, __u64 flags,
  *  Error code
  */
 extern int bpf_dynptr_from_xdp(struct xdp_md *xdp, __u64 flags,
-			       struct bpf_dynptr *ptr__uninit) __ksym;
+			       struct bpf_dynptr *ptr__uninit) __ksym __weak;
 
 /* Description
  *  Obtain a read-only pointer to the dynptr's data
@@ -26,7 +26,7 @@ extern int bpf_dynptr_from_xdp(struct xdp_md *xdp, __u64 flags,
  *  buffer if unable to obtain a direct pointer
  */
 extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, __u32 offset,
-			      void *buffer, __u32 buffer__szk) __ksym;
+			      void *buffer, __u32 buffer__szk) __ksym __weak;
 
 /* Description
  *  Obtain a read-write pointer to the dynptr's data
@@ -35,13 +35,13 @@ extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, __u32 offset,
  *  buffer if unable to obtain a direct pointer
  */
 extern void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr *ptr, __u32 offset,
-			      void *buffer, __u32 buffer__szk) __ksym;
+			      void *buffer, __u32 buffer__szk) __ksym __weak;
 
-extern int bpf_dynptr_adjust(const struct bpf_dynptr *ptr, __u32 start, __u32 end) __ksym;
-extern bool bpf_dynptr_is_null(const struct bpf_dynptr *ptr) __ksym;
-extern bool bpf_dynptr_is_rdonly(const struct bpf_dynptr *ptr) __ksym;
-extern __u32 bpf_dynptr_size(const struct bpf_dynptr *ptr) __ksym;
-extern int bpf_dynptr_clone(const struct bpf_dynptr *ptr, struct bpf_dynptr *clone__init) __ksym;
+extern int bpf_dynptr_adjust(const struct bpf_dynptr *ptr, __u32 start, __u32 end) __ksym __weak;
+extern bool bpf_dynptr_is_null(const struct bpf_dynptr *ptr) __ksym __weak;
+extern bool bpf_dynptr_is_rdonly(const struct bpf_dynptr *ptr) __ksym __weak;
+extern __u32 bpf_dynptr_size(const struct bpf_dynptr *ptr) __ksym __weak;
+extern int bpf_dynptr_clone(const struct bpf_dynptr *ptr, struct bpf_dynptr *clone__init) __ksym __weak;
 
 /* Description
  *  Modify the address of a AF_UNIX sockaddr.
@@ -51,9 +51,19 @@ extern int bpf_dynptr_clone(const struct bpf_dynptr *ptr, struct bpf_dynptr *clo
 extern int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern,
 				      const __u8 *sun_path, __u32 sun_path__sz) __ksym;
 
+/* Description
+ *  Allocate and configure a reqsk and link it with a listener and skb.
+ * Returns
+ *  Error code
+ */
+struct sock;
+struct bpf_tcp_req_attrs;
+extern int bpf_sk_assign_tcp_reqsk(struct __sk_buff *skb, struct sock *sk,
+				   struct bpf_tcp_req_attrs *attrs, int attrs__sz) __ksym;
+
 void *bpf_cast_to_kern_ctx(void *) __ksym;
 
-void *bpf_rdonly_cast(void *obj, __u32 btf_id) __ksym;
+extern void *bpf_rdonly_cast(const void *obj, __u32 btf_id) __ksym __weak;
 
 extern int bpf_get_file_xattr(struct file *file, const char *name,
 			      struct bpf_dynptr *value_ptr) __ksym;
diff --git a/tools/testing/selftests/bpf/bpf_test_no_cfi/Makefile b/tools/testing/selftests/bpf/bpf_test_no_cfi/Makefile
new file mode 100644
index 0000000000..ed5143b79e
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_test_no_cfi/Makefile
@@ -0,0 +1,19 @@
+BPF_TEST_NO_CFI_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST)))))
+KDIR ?= $(abspath $(BPF_TEST_NO_CFI_DIR)/../../../../..)
+
+ifeq ($(V),1)
+Q =
+else
+Q = @
+endif
+
+MODULES = bpf_test_no_cfi.ko
+
+obj-m += bpf_test_no_cfi.o
+
+all:
+	+$(Q)make -C $(KDIR) M=$(BPF_TEST_NO_CFI_DIR) modules
+
+clean:
+	+$(Q)make -C $(KDIR) M=$(BPF_TEST_NO_CFI_DIR) clean
+
diff --git a/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c b/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c
new file mode 100644
index 0000000000..b1dd889d5d
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c
@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/init.h>
+#include <linux/module.h>
+
+struct bpf_test_no_cfi_ops {
+	void (*fn_1)(void);
+	void (*fn_2)(void);
+};
+
+static int dummy_init(struct btf *btf)
+{
+	return 0;
+}
+
+static int dummy_init_member(const struct btf_type *t,
+			     const struct btf_member *member,
+			     void *kdata, const void *udata)
+{
+	return 0;
+}
+
+static int dummy_reg(void *kdata)
+{
+	return 0;
+}
+
+static void dummy_unreg(void *kdata)
+{
+}
+
+static const struct bpf_verifier_ops dummy_verifier_ops;
+
+static void bpf_test_no_cfi_ops__fn_1(void)
+{
+}
+
+static void bpf_test_no_cfi_ops__fn_2(void)
+{
+}
+
+static struct bpf_test_no_cfi_ops __test_no_cif_ops = {
+	.fn_1 = bpf_test_no_cfi_ops__fn_1,
+	.fn_2 = bpf_test_no_cfi_ops__fn_2,
+};
+
+static struct bpf_struct_ops test_no_cif_ops = {
+	.verifier_ops = &dummy_verifier_ops,
+	.init = dummy_init,
+	.init_member = dummy_init_member,
+	.reg = dummy_reg,
+	.unreg = dummy_unreg,
+	.name = "bpf_test_no_cfi_ops",
+	.owner = THIS_MODULE,
+};
+
+static int bpf_test_no_cfi_init(void)
+{
+	int ret;
+
+	ret = register_bpf_struct_ops(&test_no_cif_ops,
+				      bpf_test_no_cfi_ops);
+	if (!ret)
+		return -EINVAL;
+
+	test_no_cif_ops.cfi_stubs = &__test_no_cif_ops;
+	ret = register_bpf_struct_ops(&test_no_cif_ops,
+				      bpf_test_no_cfi_ops);
+	return ret;
+}
+
+static void bpf_test_no_cfi_exit(void)
+{
+}
+
+module_init(bpf_test_no_cfi_init);
+module_exit(bpf_test_no_cfi_exit);
+
+MODULE_AUTHOR("Kuifeng Lee");
+MODULE_DESCRIPTION("BPF no cfi_stubs test module");
+MODULE_LICENSE("Dual BSD/GPL");
+
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index e7c9e1c7fd..edcd261065 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
+#include <linux/bpf.h>
 #include <linux/btf.h>
 #include <linux/btf_ids.h>
 #include <linux/delay.h>
@@ -204,6 +205,9 @@ __weak noinline struct file *bpf_testmod_return_ptr(int arg)
 	case 5: return (void *)~(1ull << 30);	/* trigger extable */
 	case 6: return &f;			/* valid addr */
 	case 7: return (void *)((long)&f | 1);	/* kernel tricks */
+#ifdef CONFIG_X86_64
+	case 8: return (void *)VSYSCALL_ADDR;   /* vsyscall page address */
+#endif
 	default: return NULL;
 	}
 }
@@ -342,12 +346,12 @@ static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = {
 	.write = bpf_testmod_test_write,
 };
 
-BTF_SET8_START(bpf_testmod_common_kfunc_ids)
+BTF_KFUNCS_START(bpf_testmod_common_kfunc_ids)
 BTF_ID_FLAGS(func, bpf_iter_testmod_seq_new, KF_ITER_NEW)
 BTF_ID_FLAGS(func, bpf_iter_testmod_seq_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_testmod_seq_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_kfunc_common_test)
-BTF_SET8_END(bpf_testmod_common_kfunc_ids)
+BTF_KFUNCS_END(bpf_testmod_common_kfunc_ids)
 
 static const struct btf_kfunc_id_set bpf_testmod_common_kfunc_set = {
 	.owner = THIS_MODULE,
@@ -493,7 +497,7 @@ __bpf_kfunc static u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused
 	return arg;
 }
 
-BTF_SET8_START(bpf_testmod_check_kfunc_ids)
+BTF_KFUNCS_START(bpf_testmod_check_kfunc_ids)
 BTF_ID_FLAGS(func, bpf_testmod_test_mod_kfunc)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test1)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test2)
@@ -519,13 +523,120 @@ BTF_ID_FLAGS(func, bpf_kfunc_call_test_ref, KF_TRUSTED_ARGS | KF_RCU)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_offset)
-BTF_SET8_END(bpf_testmod_check_kfunc_ids)
+BTF_KFUNCS_END(bpf_testmod_check_kfunc_ids)
+
+static int bpf_testmod_ops_init(struct btf *btf)
+{
+	return 0;
+}
+
+static bool bpf_testmod_ops_is_valid_access(int off, int size,
+					    enum bpf_access_type type,
+					    const struct bpf_prog *prog,
+					    struct bpf_insn_access_aux *info)
+{
+	return bpf_tracing_btf_ctx_access(off, size, type, prog, info);
+}
+
+static int bpf_testmod_ops_init_member(const struct btf_type *t,
+				       const struct btf_member *member,
+				       void *kdata, const void *udata)
+{
+	if (member->offset == offsetof(struct bpf_testmod_ops, data) * 8) {
+		/* For data fields, this function has to copy it and return
+		 * 1 to indicate that the data has been handled by the
+		 * struct_ops type, or the verifier will reject the map if
+		 * the value of the data field is not zero.
+		 */
+		((struct bpf_testmod_ops *)kdata)->data = ((struct bpf_testmod_ops *)udata)->data;
+		return 1;
+	}
+	return 0;
+}
 
 static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = {
 	.owner = THIS_MODULE,
 	.set   = &bpf_testmod_check_kfunc_ids,
 };
 
+static const struct bpf_verifier_ops bpf_testmod_verifier_ops = {
+	.is_valid_access = bpf_testmod_ops_is_valid_access,
+};
+
+static int bpf_dummy_reg(void *kdata)
+{
+	struct bpf_testmod_ops *ops = kdata;
+
+	if (ops->test_1)
+		ops->test_1();
+	/* Some test cases (ex. struct_ops_maybe_null) may not have test_2
+	 * initialized, so we need to check for NULL.
+	 */
+	if (ops->test_2)
+		ops->test_2(4, ops->data);
+
+	return 0;
+}
+
+static void bpf_dummy_unreg(void *kdata)
+{
+}
+
+static int bpf_testmod_test_1(void)
+{
+	return 0;
+}
+
+static void bpf_testmod_test_2(int a, int b)
+{
+}
+
+static int bpf_testmod_ops__test_maybe_null(int dummy,
+					    struct task_struct *task__nullable)
+{
+	return 0;
+}
+
+static struct bpf_testmod_ops __bpf_testmod_ops = {
+	.test_1 = bpf_testmod_test_1,
+	.test_2 = bpf_testmod_test_2,
+	.test_maybe_null = bpf_testmod_ops__test_maybe_null,
+};
+
+struct bpf_struct_ops bpf_bpf_testmod_ops = {
+	.verifier_ops = &bpf_testmod_verifier_ops,
+	.init = bpf_testmod_ops_init,
+	.init_member = bpf_testmod_ops_init_member,
+	.reg = bpf_dummy_reg,
+	.unreg = bpf_dummy_unreg,
+	.cfi_stubs = &__bpf_testmod_ops,
+	.name = "bpf_testmod_ops",
+	.owner = THIS_MODULE,
+};
+
+static int bpf_dummy_reg2(void *kdata)
+{
+	struct bpf_testmod_ops2 *ops = kdata;
+
+	ops->test_1();
+	return 0;
+}
+
+static struct bpf_testmod_ops2 __bpf_testmod_ops2 = {
+	.test_1 = bpf_testmod_test_1,
+};
+
+struct bpf_struct_ops bpf_testmod_ops2 = {
+	.verifier_ops = &bpf_testmod_verifier_ops,
+	.init = bpf_testmod_ops_init,
+	.init_member = bpf_testmod_ops_init_member,
+	.reg = bpf_dummy_reg2,
+	.unreg = bpf_dummy_unreg,
+	.cfi_stubs = &__bpf_testmod_ops2,
+	.name = "bpf_testmod_ops2",
+	.owner = THIS_MODULE,
+};
+
 extern int bpf_fentry_test1(int a);
 
 static int bpf_testmod_init(void)
@@ -536,6 +647,8 @@ static int bpf_testmod_init(void)
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_testmod_kfunc_set);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_testmod_kfunc_set);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &bpf_testmod_kfunc_set);
+	ret = ret ?: register_bpf_struct_ops(&bpf_bpf_testmod_ops, bpf_testmod_ops);
+	ret = ret ?: register_bpf_struct_ops(&bpf_testmod_ops2, bpf_testmod_ops2);
 	if (ret < 0)
 		return ret;
 	if (bpf_fentry_test1(0) < 0)
@@ -553,7 +666,7 @@ static void bpf_testmod_exit(void)
 	while (refcount_read(&prog_test_struct.cnt) > 1)
 		msleep(20);
 
-	return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
+	sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
 }
 
 module_init(bpf_testmod_init);
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
index f32793efe0..23fa1872ee 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
@@ -5,6 +5,8 @@
 
 #include <linux/types.h>
 
+struct task_struct;
+
 struct bpf_testmod_test_read_ctx {
 	char *buf;
 	loff_t off;
@@ -28,4 +30,67 @@ struct bpf_iter_testmod_seq {
 	int cnt;
 };
 
+struct bpf_testmod_ops {
+	int (*test_1)(void);
+	void (*test_2)(int a, int b);
+	/* Used to test nullable arguments. */
+	int (*test_maybe_null)(int dummy, struct task_struct *task);
+
+	/* The following fields are used to test shadow copies. */
+	char onebyte;
+	struct {
+		int a;
+		int b;
+	} unsupported;
+	int data;
+
+	/* The following pointers are used to test the maps having multiple
+	 * pages of trampolines.
+	 */
+	int (*tramp_1)(int value);
+	int (*tramp_2)(int value);
+	int (*tramp_3)(int value);
+	int (*tramp_4)(int value);
+	int (*tramp_5)(int value);
+	int (*tramp_6)(int value);
+	int (*tramp_7)(int value);
+	int (*tramp_8)(int value);
+	int (*tramp_9)(int value);
+	int (*tramp_10)(int value);
+	int (*tramp_11)(int value);
+	int (*tramp_12)(int value);
+	int (*tramp_13)(int value);
+	int (*tramp_14)(int value);
+	int (*tramp_15)(int value);
+	int (*tramp_16)(int value);
+	int (*tramp_17)(int value);
+	int (*tramp_18)(int value);
+	int (*tramp_19)(int value);
+	int (*tramp_20)(int value);
+	int (*tramp_21)(int value);
+	int (*tramp_22)(int value);
+	int (*tramp_23)(int value);
+	int (*tramp_24)(int value);
+	int (*tramp_25)(int value);
+	int (*tramp_26)(int value);
+	int (*tramp_27)(int value);
+	int (*tramp_28)(int value);
+	int (*tramp_29)(int value);
+	int (*tramp_30)(int value);
+	int (*tramp_31)(int value);
+	int (*tramp_32)(int value);
+	int (*tramp_33)(int value);
+	int (*tramp_34)(int value);
+	int (*tramp_35)(int value);
+	int (*tramp_36)(int value);
+	int (*tramp_37)(int value);
+	int (*tramp_38)(int value);
+	int (*tramp_39)(int value);
+	int (*tramp_40)(int value);
+};
+
+struct bpf_testmod_ops2 {
+	int (*test_1)(void);
+};
+
 #endif /* _BPF_TESTMOD_H */
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index e812876d79..19be9c63d5 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -508,9 +508,6 @@ int cgroup_setup_and_join(const char *path) {
 /**
  * setup_classid_environment() - Setup the cgroupv1 net_cls environment
  *
- * This function should only be called in a custom mount namespace, e.g.
- * created by running setup_cgroup_environment.
- *
  * After calling this function, cleanup_classid_environment should be called
  * once testing is complete.
  *
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index c125c441ab..01f241ea2c 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -81,6 +81,7 @@ CONFIG_NF_NAT=y
 CONFIG_RC_CORE=y
 CONFIG_SECURITY=y
 CONFIG_SECURITYFS=y
+CONFIG_SYN_COOKIES=y
 CONFIG_TEST_BPF=m
 CONFIG_USERFAULTFD=y
 CONFIG_VSOCKETS=y
diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index be96bf0223..6db27a9088 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -461,8 +461,6 @@ struct nstoken *open_netns(const char *name)
 
 	return token;
 fail:
-	if (token->orig_netns_fd != -1)
-		close(token->orig_netns_fd);
 	free(token);
 	return NULL;
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/arena_htab.c b/tools/testing/selftests/bpf/prog_tests/arena_htab.c
new file mode 100644
index 0000000000..d69fd2465f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/arena_htab.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <sys/mman.h>
+#include <network_helpers.h>
+#include <sys/user.h>
+#ifndef PAGE_SIZE /* on some archs it comes in sys/user.h */
+#include <unistd.h>
+#define PAGE_SIZE getpagesize()
+#endif
+#include "arena_htab_asm.skel.h"
+#include "arena_htab.skel.h"
+
+#include "bpf_arena_htab.h"
+
+static void test_arena_htab_common(struct htab *htab)
+{
+	int i;
+
+	printf("htab %p buckets %p n_buckets %d\n", htab, htab->buckets, htab->n_buckets);
+	ASSERT_OK_PTR(htab->buckets, "htab->buckets shouldn't be NULL");
+	for (i = 0; htab->buckets && i < 16; i += 4) {
+		/*
+		 * Walk htab buckets and link lists since all pointers are correct,
+		 * though they were written by bpf program.
+		 */
+		int val = htab_lookup_elem(htab, i);
+
+		ASSERT_EQ(i, val, "key == value");
+	}
+}
+
+static void test_arena_htab_llvm(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	struct arena_htab *skel;
+	struct htab *htab;
+	size_t arena_sz;
+	void *area;
+	int ret;
+
+	skel = arena_htab__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "arena_htab__open_and_load"))
+		return;
+
+	area = bpf_map__initial_value(skel->maps.arena, &arena_sz);
+	/* fault-in a page with pgoff == 0 as sanity check */
+	*(volatile int *)area = 0x55aa;
+
+	/* bpf prog will allocate more pages */
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.arena_htab_llvm), &opts);
+	ASSERT_OK(ret, "ret");
+	ASSERT_OK(opts.retval, "retval");
+	if (skel->bss->skip) {
+		printf("%s:SKIP:compiler doesn't support arena_cast\n", __func__);
+		test__skip();
+		goto out;
+	}
+	htab = skel->bss->htab_for_user;
+	test_arena_htab_common(htab);
+out:
+	arena_htab__destroy(skel);
+}
+
+static void test_arena_htab_asm(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	struct arena_htab_asm *skel;
+	struct htab *htab;
+	int ret;
+
+	skel = arena_htab_asm__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "arena_htab_asm__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.arena_htab_asm), &opts);
+	ASSERT_OK(ret, "ret");
+	ASSERT_OK(opts.retval, "retval");
+	htab = skel->bss->htab_for_user;
+	test_arena_htab_common(htab);
+	arena_htab_asm__destroy(skel);
+}
+
+void test_arena_htab(void)
+{
+	if (test__start_subtest("arena_htab_llvm"))
+		test_arena_htab_llvm();
+	if (test__start_subtest("arena_htab_asm"))
+		test_arena_htab_asm();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/arena_list.c b/tools/testing/selftests/bpf/prog_tests/arena_list.c
new file mode 100644
index 0000000000..d15867cddd
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/arena_list.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <sys/mman.h>
+#include <network_helpers.h>
+#include <sys/user.h>
+#ifndef PAGE_SIZE /* on some archs it comes in sys/user.h */
+#include <unistd.h>
+#define PAGE_SIZE getpagesize()
+#endif
+
+#include "bpf_arena_list.h"
+#include "arena_list.skel.h"
+
+struct elem {
+	struct arena_list_node node;
+	__u64 value;
+};
+
+static int list_sum(struct arena_list_head *head)
+{
+	struct elem __arena *n;
+	int sum = 0;
+
+	list_for_each_entry(n, head, node)
+		sum += n->value;
+	return sum;
+}
+
+static void test_arena_list_add_del(int cnt)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	struct arena_list *skel;
+	int expected_sum = (u64)cnt * (cnt - 1) / 2;
+	int ret, sum;
+
+	skel = arena_list__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "arena_list__open_and_load"))
+		return;
+
+	skel->bss->cnt = cnt;
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.arena_list_add), &opts);
+	ASSERT_OK(ret, "ret_add");
+	ASSERT_OK(opts.retval, "retval");
+	if (skel->bss->skip) {
+		printf("%s:SKIP:compiler doesn't support arena_cast\n", __func__);
+		test__skip();
+		goto out;
+	}
+	sum = list_sum(skel->bss->list_head);
+	ASSERT_EQ(sum, expected_sum, "sum of elems");
+	ASSERT_EQ(skel->arena->arena_sum, expected_sum, "__arena sum of elems");
+	ASSERT_EQ(skel->arena->test_val, cnt + 1, "num of elems");
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.arena_list_del), &opts);
+	ASSERT_OK(ret, "ret_del");
+	sum = list_sum(skel->bss->list_head);
+	ASSERT_EQ(sum, 0, "sum of list elems after del");
+	ASSERT_EQ(skel->bss->list_sum, expected_sum, "sum of list elems computed by prog");
+	ASSERT_EQ(skel->arena->arena_sum, expected_sum, "__arena sum of elems");
+out:
+	arena_list__destroy(skel);
+}
+
+void test_arena_list(void)
+{
+	if (test__start_subtest("arena_list_1"))
+		test_arena_list_add_del(1);
+	if (test__start_subtest("arena_list_1000"))
+		test_arena_list_add_del(1000);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bad_struct_ops.c b/tools/testing/selftests/bpf/prog_tests/bad_struct_ops.c
new file mode 100644
index 0000000000..6a707213e4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bad_struct_ops.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "bad_struct_ops.skel.h"
+#include "bad_struct_ops2.skel.h"
+
+static void invalid_prog_reuse(void)
+{
+	struct bad_struct_ops *skel;
+	char *log = NULL;
+	int err;
+
+	skel = bad_struct_ops__open();
+	if (!ASSERT_OK_PTR(skel, "bad_struct_ops__open"))
+		return;
+
+	if (start_libbpf_log_capture())
+		goto cleanup;
+
+	err = bad_struct_ops__load(skel);
+	log = stop_libbpf_log_capture();
+	ASSERT_ERR(err, "bad_struct_ops__load should fail");
+	ASSERT_HAS_SUBSTR(log,
+		"struct_ops init_kern testmod_2 func ptr test_1: invalid reuse of prog test_1",
+		"expected init_kern message");
+
+cleanup:
+	free(log);
+	bad_struct_ops__destroy(skel);
+}
+
+static void unused_program(void)
+{
+	struct bad_struct_ops2 *skel;
+	char *log = NULL;
+	int err;
+
+	skel = bad_struct_ops2__open();
+	if (!ASSERT_OK_PTR(skel, "bad_struct_ops2__open"))
+		return;
+
+	/* struct_ops programs not referenced from any maps are open
+	 * with autoload set to true.
+	 */
+	ASSERT_TRUE(bpf_program__autoload(skel->progs.foo), "foo autoload == true");
+
+	if (start_libbpf_log_capture())
+		goto cleanup;
+
+	err = bad_struct_ops2__load(skel);
+	ASSERT_ERR(err, "bad_struct_ops2__load should fail");
+	log = stop_libbpf_log_capture();
+	ASSERT_HAS_SUBSTR(log, "prog 'foo': failed to load",
+			  "message about 'foo' failing to load");
+
+cleanup:
+	free(log);
+	bad_struct_ops2__destroy(skel);
+}
+
+void test_bad_struct_ops(void)
+{
+	if (test__start_subtest("invalid_prog_reuse"))
+		invalid_prog_reuse();
+	if (test__start_subtest("unused_program"))
+		unused_program();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
index e770912fc1..4c6ada5b27 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
@@ -35,7 +35,7 @@ static int check_load(const char *file, enum bpf_prog_type type)
 	}
 
 	bpf_program__set_type(prog, type);
-	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS);
+	bpf_program__set_flags(prog, testing_prog_flags());
 	bpf_program__set_log_level(prog, 4 | extra_prog_load_log_flags);
 
 	err = bpf_object__load(obj);
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 816145bcb6..00965a6e83 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -3535,6 +3535,32 @@ static struct btf_raw_test raw_tests[] = {
 	.value_type_id = 1,
 	.max_entries = 1,
 },
+{
+	.descr = "datasec: name '?.foo bar:buz' is ok",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* VAR x */                                     /* [2] */
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
+		BTF_VAR_STATIC,
+		/* DATASEC ?.data */                            /* [3] */
+		BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(2, 0, 4),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0x\0?.foo bar:buz"),
+},
+{
+	.descr = "type name '?foo' is not ok",
+	.raw_types = {
+		/* union ?foo; */
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_FWD, 1, 0), 0), /* [1] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0?foo"),
+	.err_str = "Invalid name",
+	.btf_load_err = true,
+},
 
 {
 	.descr = "float test #1, well-formed",
@@ -4363,6 +4389,9 @@ static void do_test_raw(unsigned int test_num)
 	if (err || btf_fd < 0)
 		goto done;
 
+	if (!test->map_type)
+		goto done;
+
 	opts.btf_fd = btf_fd;
 	opts.btf_key_type_id = test->key_type_id;
 	opts.btf_value_type_id = test->value_type_id;
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c b/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c
index 25332e5967..74d6d7546f 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c
@@ -87,12 +87,9 @@ void test_cgroup1_hierarchy(void)
 		goto destroy;
 
 	/* Setup cgroup1 hierarchy */
-	err = setup_cgroup_environment();
-	if (!ASSERT_OK(err, "setup_cgroup_environment"))
-		goto destroy;
 	err = setup_classid_environment();
 	if (!ASSERT_OK(err, "setup_classid_environment"))
-		goto cleanup_cgroup;
+		goto destroy;
 
 	err = join_classid();
 	if (!ASSERT_OK(err, "join_cgroup1"))
@@ -156,8 +153,6 @@ void test_cgroup1_hierarchy(void)
 
 cleanup:
 	cleanup_classid_environment();
-cleanup_cgroup:
-	cleanup_cgroup_environment();
 destroy:
 	test_cgroup1_hierarchy__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/cpumask.c b/tools/testing/selftests/bpf/prog_tests/cpumask.c
index c2e886399e..ecf89df781 100644
--- a/tools/testing/selftests/bpf/prog_tests/cpumask.c
+++ b/tools/testing/selftests/bpf/prog_tests/cpumask.c
@@ -27,7 +27,7 @@ static void verify_success(const char *prog_name)
 	struct bpf_program *prog;
 	struct bpf_link *link = NULL;
 	pid_t child_pid;
-	int status;
+	int status, err;
 
 	skel = cpumask_success__open();
 	if (!ASSERT_OK_PTR(skel, "cpumask_success__open"))
@@ -36,8 +36,8 @@ static void verify_success(const char *prog_name)
 	skel->bss->pid = getpid();
 	skel->bss->nr_cpus = libbpf_num_possible_cpus();
 
-	cpumask_success__load(skel);
-	if (!ASSERT_OK_PTR(skel, "cpumask_success__load"))
+	err = cpumask_success__load(skel);
+	if (!ASSERT_OK(err, "cpumask_success__load"))
 		goto cleanup;
 
 	prog = bpf_object__find_program_by_name(skel->obj, prog_name);
diff --git a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
index 4951aa978f..3b7c57fe55 100644
--- a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
+++ b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
@@ -626,50 +626,6 @@ err:
 	return false;
 }
 
-/* Request BPF program instructions after all rewrites are applied,
- * e.g. verifier.c:convert_ctx_access() is done.
- */
-static int get_xlated_program(int fd_prog, struct bpf_insn **buf, __u32 *cnt)
-{
-	struct bpf_prog_info info = {};
-	__u32 info_len = sizeof(info);
-	__u32 xlated_prog_len;
-	__u32 buf_element_size = sizeof(struct bpf_insn);
-
-	if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) {
-		perror("bpf_prog_get_info_by_fd failed");
-		return -1;
-	}
-
-	xlated_prog_len = info.xlated_prog_len;
-	if (xlated_prog_len % buf_element_size) {
-		printf("Program length %d is not multiple of %d\n",
-		       xlated_prog_len, buf_element_size);
-		return -1;
-	}
-
-	*cnt = xlated_prog_len / buf_element_size;
-	*buf = calloc(*cnt, buf_element_size);
-	if (!buf) {
-		perror("can't allocate xlated program buffer");
-		return -ENOMEM;
-	}
-
-	bzero(&info, sizeof(info));
-	info.xlated_prog_len = xlated_prog_len;
-	info.xlated_prog_insns = (__u64)(unsigned long)*buf;
-	if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) {
-		perror("second bpf_prog_get_info_by_fd failed");
-		goto out_free_buf;
-	}
-
-	return 0;
-
-out_free_buf:
-	free(*buf);
-	return -1;
-}
-
 static void print_insn(void *private_data, const char *fmt, ...)
 {
 	va_list args;
diff --git a/tools/testing/selftests/bpf/prog_tests/decap_sanity.c b/tools/testing/selftests/bpf/prog_tests/decap_sanity.c
index 5c0ebe6ba8..dcb9e5070c 100644
--- a/tools/testing/selftests/bpf/prog_tests/decap_sanity.c
+++ b/tools/testing/selftests/bpf/prog_tests/decap_sanity.c
@@ -72,6 +72,6 @@ fail:
 		bpf_tc_hook_destroy(&qdisc_hook);
 		close_netns(nstoken);
 	}
-	SYS_NOFAIL("ip netns del " NS_TEST " &> /dev/null");
+	SYS_NOFAIL("ip netns del " NS_TEST);
 	decap_sanity__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fib_lookup.c b/tools/testing/selftests/bpf/prog_tests/fib_lookup.c
index 4ad4cd6915..3379df2d4c 100644
--- a/tools/testing/selftests/bpf/prog_tests/fib_lookup.c
+++ b/tools/testing/selftests/bpf/prog_tests/fib_lookup.c
@@ -298,6 +298,6 @@ void test_fib_lookup(void)
 fail:
 	if (nstoken)
 		close_netns(nstoken);
-	SYS_NOFAIL("ip netns del " NS_TEST " &> /dev/null");
+	SYS_NOFAIL("ip netns del " NS_TEST);
 	fib_lookup__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
index d4b1901f78..f3932941bb 100644
--- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
+++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
@@ -19,6 +19,7 @@ static const char *kmulti_syms[] = {
 };
 #define KMULTI_CNT ARRAY_SIZE(kmulti_syms)
 static __u64 kmulti_addrs[KMULTI_CNT];
+static __u64 kmulti_cookies[] = { 3, 1, 2 };
 
 #define KPROBE_FUNC "bpf_fentry_test1"
 static __u64 kprobe_addr;
@@ -31,6 +32,8 @@ static noinline void uprobe_func(void)
 	asm volatile ("");
 }
 
+#define PERF_EVENT_COOKIE 0xdeadbeef
+
 static int verify_perf_link_info(int fd, enum bpf_perf_event_type type, long addr,
 				 ssize_t offset, ssize_t entry_offset)
 {
@@ -62,6 +65,8 @@ again:
 			ASSERT_EQ(info.perf_event.kprobe.addr, addr + entry_offset,
 				  "kprobe_addr");
 
+		ASSERT_EQ(info.perf_event.kprobe.cookie, PERF_EVENT_COOKIE, "kprobe_cookie");
+
 		if (!info.perf_event.kprobe.func_name) {
 			ASSERT_EQ(info.perf_event.kprobe.name_len, 0, "name_len");
 			info.perf_event.kprobe.func_name = ptr_to_u64(&buf);
@@ -81,6 +86,8 @@ again:
 			goto again;
 		}
 
+		ASSERT_EQ(info.perf_event.tracepoint.cookie, PERF_EVENT_COOKIE, "tracepoint_cookie");
+
 		err = strncmp(u64_to_ptr(info.perf_event.tracepoint.tp_name), TP_NAME,
 			      strlen(TP_NAME));
 		ASSERT_EQ(err, 0, "cmp_tp_name");
@@ -96,10 +103,17 @@ again:
 			goto again;
 		}
 
+		ASSERT_EQ(info.perf_event.uprobe.cookie, PERF_EVENT_COOKIE, "uprobe_cookie");
+
 		err = strncmp(u64_to_ptr(info.perf_event.uprobe.file_name), UPROBE_FILE,
 			      strlen(UPROBE_FILE));
 			ASSERT_EQ(err, 0, "cmp_file_name");
 		break;
+	case BPF_PERF_EVENT_EVENT:
+		ASSERT_EQ(info.perf_event.event.type, PERF_TYPE_SOFTWARE, "event_type");
+		ASSERT_EQ(info.perf_event.event.config, PERF_COUNT_SW_PAGE_FAULTS, "event_config");
+		ASSERT_EQ(info.perf_event.event.cookie, PERF_EVENT_COOKIE, "event_cookie");
+		break;
 	default:
 		err = -1;
 		break;
@@ -139,6 +153,7 @@ static void test_kprobe_fill_link_info(struct test_fill_link_info *skel,
 	DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts,
 		.attach_mode = PROBE_ATTACH_MODE_LINK,
 		.retprobe = type == BPF_PERF_EVENT_KRETPROBE,
+		.bpf_cookie = PERF_EVENT_COOKIE,
 	);
 	ssize_t entry_offset = 0;
 	struct bpf_link *link;
@@ -163,10 +178,13 @@ static void test_kprobe_fill_link_info(struct test_fill_link_info *skel,
 
 static void test_tp_fill_link_info(struct test_fill_link_info *skel)
 {
+	DECLARE_LIBBPF_OPTS(bpf_tracepoint_opts, opts,
+		.bpf_cookie = PERF_EVENT_COOKIE,
+	);
 	struct bpf_link *link;
 	int link_fd, err;
 
-	link = bpf_program__attach_tracepoint(skel->progs.tp_run, TP_CAT, TP_NAME);
+	link = bpf_program__attach_tracepoint_opts(skel->progs.tp_run, TP_CAT, TP_NAME, &opts);
 	if (!ASSERT_OK_PTR(link, "attach_tp"))
 		return;
 
@@ -176,16 +194,53 @@ static void test_tp_fill_link_info(struct test_fill_link_info *skel)
 	bpf_link__destroy(link);
 }
 
+static void test_event_fill_link_info(struct test_fill_link_info *skel)
+{
+	DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, opts,
+		.bpf_cookie = PERF_EVENT_COOKIE,
+	);
+	struct bpf_link *link;
+	int link_fd, err, pfd;
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_PAGE_FAULTS,
+		.freq = 1,
+		.sample_freq = 1,
+		.size = sizeof(struct perf_event_attr),
+	};
+
+	pfd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, 0 /* cpu 0 */,
+		      -1 /* group id */, 0 /* flags */);
+	if (!ASSERT_GE(pfd, 0, "perf_event_open"))
+		return;
+
+	link = bpf_program__attach_perf_event_opts(skel->progs.event_run, pfd, &opts);
+	if (!ASSERT_OK_PTR(link, "attach_event"))
+		goto error;
+
+	link_fd = bpf_link__fd(link);
+	err = verify_perf_link_info(link_fd, BPF_PERF_EVENT_EVENT, 0, 0, 0);
+	ASSERT_OK(err, "verify_perf_link_info");
+	bpf_link__destroy(link);
+
+error:
+	close(pfd);
+}
+
 static void test_uprobe_fill_link_info(struct test_fill_link_info *skel,
 				       enum bpf_perf_event_type type)
 {
+	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts,
+		.retprobe = type == BPF_PERF_EVENT_URETPROBE,
+		.bpf_cookie = PERF_EVENT_COOKIE,
+	);
 	struct bpf_link *link;
 	int link_fd, err;
 
-	link = bpf_program__attach_uprobe(skel->progs.uprobe_run,
-					  type == BPF_PERF_EVENT_URETPROBE,
-					  0, /* self pid */
-					  UPROBE_FILE, uprobe_offset);
+	link = bpf_program__attach_uprobe_opts(skel->progs.uprobe_run,
+					       0, /* self pid */
+					       UPROBE_FILE, uprobe_offset,
+					       &opts);
 	if (!ASSERT_OK_PTR(link, "attach_uprobe"))
 		return;
 
@@ -195,11 +250,11 @@ static void test_uprobe_fill_link_info(struct test_fill_link_info *skel,
 	bpf_link__destroy(link);
 }
 
-static int verify_kmulti_link_info(int fd, bool retprobe)
+static int verify_kmulti_link_info(int fd, bool retprobe, bool has_cookies)
 {
+	__u64 addrs[KMULTI_CNT], cookies[KMULTI_CNT];
 	struct bpf_link_info info;
 	__u32 len = sizeof(info);
-	__u64 addrs[KMULTI_CNT];
 	int flags, i, err;
 
 	memset(&info, 0, sizeof(info));
@@ -221,18 +276,22 @@ again:
 
 	if (!info.kprobe_multi.addrs) {
 		info.kprobe_multi.addrs = ptr_to_u64(addrs);
+		info.kprobe_multi.cookies = ptr_to_u64(cookies);
 		goto again;
 	}
-	for (i = 0; i < KMULTI_CNT; i++)
+	for (i = 0; i < KMULTI_CNT; i++) {
 		ASSERT_EQ(addrs[i], kmulti_addrs[i], "kmulti_addrs");
+		ASSERT_EQ(cookies[i], has_cookies ? kmulti_cookies[i] : 0,
+			  "kmulti_cookies_value");
+	}
 	return 0;
 }
 
 static void verify_kmulti_invalid_user_buffer(int fd)
 {
+	__u64 addrs[KMULTI_CNT], cookies[KMULTI_CNT];
 	struct bpf_link_info info;
 	__u32 len = sizeof(info);
-	__u64 addrs[KMULTI_CNT];
 	int err, i;
 
 	memset(&info, 0, sizeof(info));
@@ -266,7 +325,20 @@ static void verify_kmulti_invalid_user_buffer(int fd)
 	info.kprobe_multi.count = KMULTI_CNT;
 	info.kprobe_multi.addrs = 0x1; /* invalid addr */
 	err = bpf_link_get_info_by_fd(fd, &info, &len);
-	ASSERT_EQ(err, -EFAULT, "invalid_buff");
+	ASSERT_EQ(err, -EFAULT, "invalid_buff_addrs");
+
+	info.kprobe_multi.count = KMULTI_CNT;
+	info.kprobe_multi.addrs = ptr_to_u64(addrs);
+	info.kprobe_multi.cookies = 0x1; /* invalid addr */
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EFAULT, "invalid_buff_cookies");
+
+	/* cookies && !count */
+	info.kprobe_multi.count = 0;
+	info.kprobe_multi.addrs = ptr_to_u64(NULL);
+	info.kprobe_multi.cookies = ptr_to_u64(cookies);
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "invalid_cookies_count");
 }
 
 static int symbols_cmp_r(const void *a, const void *b)
@@ -278,13 +350,15 @@ static int symbols_cmp_r(const void *a, const void *b)
 }
 
 static void test_kprobe_multi_fill_link_info(struct test_fill_link_info *skel,
-					     bool retprobe, bool invalid)
+					     bool retprobe, bool cookies,
+					     bool invalid)
 {
 	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
 	struct bpf_link *link;
 	int link_fd, err;
 
 	opts.syms = kmulti_syms;
+	opts.cookies = cookies ? kmulti_cookies : NULL;
 	opts.cnt = KMULTI_CNT;
 	opts.retprobe = retprobe;
 	link = bpf_program__attach_kprobe_multi_opts(skel->progs.kmulti_run, NULL, &opts);
@@ -293,7 +367,7 @@ static void test_kprobe_multi_fill_link_info(struct test_fill_link_info *skel,
 
 	link_fd = bpf_link__fd(link);
 	if (!invalid) {
-		err = verify_kmulti_link_info(link_fd, retprobe);
+		err = verify_kmulti_link_info(link_fd, retprobe, cookies);
 		ASSERT_OK(err, "verify_kmulti_link_info");
 	} else {
 		verify_kmulti_invalid_user_buffer(link_fd);
@@ -513,6 +587,8 @@ void test_fill_link_info(void)
 		test_kprobe_fill_link_info(skel, BPF_PERF_EVENT_KPROBE, true);
 	if (test__start_subtest("tracepoint_link_info"))
 		test_tp_fill_link_info(skel);
+	if (test__start_subtest("event_link_info"))
+		test_event_fill_link_info(skel);
 
 	uprobe_offset = get_uprobe_offset(&uprobe_func);
 	if (test__start_subtest("uprobe_link_info"))
@@ -523,12 +599,16 @@ void test_fill_link_info(void)
 	qsort(kmulti_syms, KMULTI_CNT, sizeof(kmulti_syms[0]), symbols_cmp_r);
 	for (i = 0; i < KMULTI_CNT; i++)
 		kmulti_addrs[i] = ksym_get_addr(kmulti_syms[i]);
-	if (test__start_subtest("kprobe_multi_link_info"))
-		test_kprobe_multi_fill_link_info(skel, false, false);
-	if (test__start_subtest("kretprobe_multi_link_info"))
-		test_kprobe_multi_fill_link_info(skel, true, false);
+	if (test__start_subtest("kprobe_multi_link_info")) {
+		test_kprobe_multi_fill_link_info(skel, false, false, false);
+		test_kprobe_multi_fill_link_info(skel, false, true, false);
+	}
+	if (test__start_subtest("kretprobe_multi_link_info")) {
+		test_kprobe_multi_fill_link_info(skel, true, false, false);
+		test_kprobe_multi_fill_link_info(skel, true, true, false);
+	}
 	if (test__start_subtest("kprobe_multi_invalid_ubuff"))
-		test_kprobe_multi_fill_link_info(skel, true, true);
+		test_kprobe_multi_fill_link_info(skel, true, true, true);
 
 	if (test__start_subtest("uprobe_multi_link_info"))
 		test_uprobe_multi_fill_link_info(skel, false, false);
diff --git a/tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c b/tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c
index 57c814f5f6..8dd2af9081 100644
--- a/tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c
+++ b/tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c
@@ -59,9 +59,9 @@ static int setup_topology(bool ipv6)
 	/* Wait for up to 5s for links to come up */
 	for (i = 0; i < 5; ++i) {
 		if (ipv6)
-			up = !system("ip netns exec " NS0 " ping -6 -c 1 -W 1 " VETH1_ADDR6 " &>/dev/null");
+			up = !SYS_NOFAIL("ip netns exec " NS0 " ping -6 -c 1 -W 1 " VETH1_ADDR6);
 		else
-			up = !system("ip netns exec " NS0 " ping -c 1 -W 1 " VETH1_ADDR " &>/dev/null");
+			up = !SYS_NOFAIL("ip netns exec " NS0 " ping -c 1 -W 1 " VETH1_ADDR);
 
 		if (up)
 			break;
diff --git a/tools/testing/selftests/bpf/prog_tests/kptr_xchg_inline.c b/tools/testing/selftests/bpf/prog_tests/kptr_xchg_inline.c
new file mode 100644
index 0000000000..7def158da9
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/kptr_xchg_inline.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <test_progs.h>
+
+#include "linux/filter.h"
+#include "kptr_xchg_inline.skel.h"
+
+void test_kptr_xchg_inline(void)
+{
+	struct kptr_xchg_inline *skel;
+	struct bpf_insn *insn = NULL;
+	struct bpf_insn exp;
+	unsigned int cnt;
+	int err;
+
+#if !(defined(__x86_64__) || defined(__aarch64__) || \
+      (defined(__riscv) && __riscv_xlen == 64))
+	test__skip();
+	return;
+#endif
+
+	skel = kptr_xchg_inline__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_load"))
+		return;
+
+	err = get_xlated_program(bpf_program__fd(skel->progs.kptr_xchg_inline), &insn, &cnt);
+	if (!ASSERT_OK(err, "prog insn"))
+		goto out;
+
+	/* The original instructions are:
+	 * r1 = map[id:xxx][0]+0
+	 * r2 = 0
+	 * call bpf_kptr_xchg#yyy
+	 *
+	 * call bpf_kptr_xchg#yyy will be inlined as:
+	 * r0 = r2
+	 * r0 = atomic64_xchg((u64 *)(r1 +0), r0)
+	 */
+	if (!ASSERT_GT(cnt, 5, "insn cnt"))
+		goto out;
+
+	exp = BPF_MOV64_REG(BPF_REG_0, BPF_REG_2);
+	if (!ASSERT_OK(memcmp(&insn[3], &exp, sizeof(exp)), "mov"))
+		goto out;
+
+	exp = BPF_ATOMIC_OP(BPF_DW, BPF_XCHG, BPF_REG_1, BPF_REG_0, 0);
+	if (!ASSERT_OK(memcmp(&insn[4], &exp, sizeof(exp)), "xchg"))
+		goto out;
+out:
+	free(insn);
+	kptr_xchg_inline__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
index 9f766ddd94..4ed46ed58a 100644
--- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
@@ -30,6 +30,8 @@ void test_libbpf_probe_prog_types(void)
 
 		if (prog_type == BPF_PROG_TYPE_UNSPEC)
 			continue;
+		if (strcmp(prog_type_name, "__MAX_BPF_PROG_TYPE") == 0)
+			continue;
 
 		if (!test__start_subtest(prog_type_name))
 			continue;
@@ -68,6 +70,8 @@ void test_libbpf_probe_map_types(void)
 
 		if (map_type == BPF_MAP_TYPE_UNSPEC)
 			continue;
+		if (strcmp(map_type_name, "__MAX_BPF_MAP_TYPE") == 0)
+			continue;
 
 		if (!test__start_subtest(map_type_name))
 			continue;
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
index eb34d612d6..62ea855ec4 100644
--- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
@@ -132,6 +132,9 @@ static void test_libbpf_bpf_map_type_str(void)
 		const char *map_type_str;
 		char buf[256];
 
+		if (map_type == __MAX_BPF_MAP_TYPE)
+			continue;
+
 		map_type_name = btf__str_by_offset(btf, e->name_off);
 		map_type_str = libbpf_bpf_map_type_str(map_type);
 		ASSERT_OK_PTR(map_type_str, map_type_name);
@@ -186,6 +189,9 @@ static void test_libbpf_bpf_prog_type_str(void)
 		const char *prog_type_str;
 		char buf[256];
 
+		if (prog_type == __MAX_BPF_PROG_TYPE)
+			continue;
+
 		prog_type_name = btf__str_by_offset(btf, e->name_off);
 		prog_type_str = libbpf_bpf_prog_type_str(prog_type);
 		ASSERT_OK_PTR(prog_type_str, prog_type_name);
diff --git a/tools/testing/selftests/bpf/prog_tests/log_fixup.c b/tools/testing/selftests/bpf/prog_tests/log_fixup.c
index 7a3fa2ff56..90a98e23be 100644
--- a/tools/testing/selftests/bpf/prog_tests/log_fixup.c
+++ b/tools/testing/selftests/bpf/prog_tests/log_fixup.c
@@ -169,9 +169,9 @@ void test_log_fixup(void)
 	if (test__start_subtest("bad_core_relo_trunc_none"))
 		bad_core_relo(0, TRUNC_NONE /* full buf */);
 	if (test__start_subtest("bad_core_relo_trunc_partial"))
-		bad_core_relo(280, TRUNC_PARTIAL /* truncate original log a bit */);
+		bad_core_relo(300, TRUNC_PARTIAL /* truncate original log a bit */);
 	if (test__start_subtest("bad_core_relo_trunc_full"))
-		bad_core_relo(220, TRUNC_FULL  /* truncate also libbpf's message patch */);
+		bad_core_relo(240, TRUNC_FULL  /* truncate also libbpf's message patch */);
 	if (test__start_subtest("bad_core_relo_subprog"))
 		bad_core_relo_subprog();
 	if (test__start_subtest("missing_map"))
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h b/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h
index e9190574e7..fb1eb8c673 100644
--- a/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h
@@ -27,8 +27,6 @@
 			}                                                     \
 	})
 
-#define NETNS "ns_lwt"
-
 static inline int netns_create(void)
 {
 	return system("ip netns add " NETNS);
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c b/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c
index 2bc932a18c..835a1d756c 100644
--- a/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c
@@ -54,6 +54,7 @@
 #include <stdbool.h>
 #include <stdlib.h>
 
+#define NETNS "ns_lwt_redirect"
 #include "lwt_helpers.h"
 #include "test_progs.h"
 #include "network_helpers.h"
@@ -85,7 +86,7 @@ static void ping_dev(const char *dev, bool is_ingress)
 		snprintf(ip, sizeof(ip), "20.0.0.%d", link_index);
 
 	/* We won't get a reply. Don't fail here */
-	SYS_NOFAIL("ping %s -c1 -W1 -s %d >/dev/null 2>&1",
+	SYS_NOFAIL("ping %s -c1 -W1 -s %d",
 		   ip, ICMP_PAYLOAD_SIZE);
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c b/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c
index f4bb2d5fca..03825d2b45 100644
--- a/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c
@@ -48,6 +48,7 @@
  *  For case 2, force UDP packets to overflow fq limit. As long as kernel
  *  is not crashed, it is considered successful.
  */
+#define NETNS "ns_lwt_reroute"
 #include "lwt_helpers.h"
 #include "network_helpers.h"
 #include <linux/net_tstamp.h>
@@ -63,7 +64,7 @@
 static void ping_once(const char *ip)
 {
 	/* We won't get a reply. Don't fail here */
-	SYS_NOFAIL("ping %s -c1 -W1 -s %d >/dev/null 2>&1",
+	SYS_NOFAIL("ping %s -c1 -W1 -s %d",
 		   ip, ICMP_PAYLOAD_SIZE);
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index 7c0be7cf55..8f8d792307 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -79,7 +79,7 @@ static void cleanup_netns(struct nstoken *nstoken)
 	if (nstoken)
 		close_netns(nstoken);
 
-	SYS_NOFAIL("ip netns del %s &> /dev/null", NS_TEST);
+	SYS_NOFAIL("ip netns del %s", NS_TEST);
 }
 
 static int verify_tsk(int map_fd, int client_fd)
diff --git a/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c b/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c
index 3f1f58d3a7..a1f7e7378a 100644
--- a/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c
@@ -29,6 +29,10 @@ static void test_success(void)
 	bpf_program__set_autoload(skel->progs.non_sleepable_1, true);
 	bpf_program__set_autoload(skel->progs.non_sleepable_2, true);
 	bpf_program__set_autoload(skel->progs.task_trusted_non_rcuptr, true);
+	bpf_program__set_autoload(skel->progs.rcu_read_lock_subprog, true);
+	bpf_program__set_autoload(skel->progs.rcu_read_lock_global_subprog, true);
+	bpf_program__set_autoload(skel->progs.rcu_read_lock_subprog_lock, true);
+	bpf_program__set_autoload(skel->progs.rcu_read_lock_subprog_unlock, true);
 	err = rcu_read_lock__load(skel);
 	if (!ASSERT_OK(err, "skel_load"))
 		goto out;
@@ -75,6 +79,8 @@ static const char * const inproper_region_tests[] = {
 	"inproper_sleepable_helper",
 	"inproper_sleepable_kfunc",
 	"nested_rcu_region",
+	"rcu_read_lock_global_subprog_lock",
+	"rcu_read_lock_global_subprog_unlock",
 };
 
 static void test_inproper_region(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
index 820d0bcfc4..eb74363f9f 100644
--- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
+++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
@@ -840,7 +840,7 @@ static int load_range_cmp_prog(struct range x, struct range y, enum op op,
 		.log_level = 2,
 		.log_buf = log_buf,
 		.log_size = log_sz,
-		.prog_flags = BPF_F_TEST_REG_INVARIANTS,
+		.prog_flags = testing_prog_flags(),
 	);
 
 	/* ; skip exit block below
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_destroy.c b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c
index b0583309a9..9c11938fe5 100644
--- a/tools/testing/selftests/bpf/prog_tests/sock_destroy.c
+++ b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c
@@ -214,7 +214,7 @@ void test_sock_destroy(void)
 cleanup:
 	if (nstoken)
 		close_netns(nstoken);
-	SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null");
+	SYS_NOFAIL("ip netns del " TEST_NS);
 	if (cgroup_fd >= 0)
 		close(cgroup_fd);
 	sock_destroy_prog__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
index 0c365f36c7..d56e18b255 100644
--- a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
+++ b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
@@ -112,7 +112,7 @@ void test_sock_iter_batch(void)
 {
 	struct nstoken *nstoken = NULL;
 
-	SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null");
+	SYS_NOFAIL("ip netns del " TEST_NS);
 	SYS(done, "ip netns add %s", TEST_NS);
 	SYS(done, "ip -net %s link set dev lo up", TEST_NS);
 
@@ -131,5 +131,5 @@ void test_sock_iter_batch(void)
 	close_netns(nstoken);
 
 done:
-	SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null");
+	SYS_NOFAIL("ip netns del " TEST_NS);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/spin_lock.c b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
index 18d451be57..2b0068742e 100644
--- a/tools/testing/selftests/bpf/prog_tests/spin_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
@@ -48,6 +48,8 @@ static struct {
 	{ "lock_id_mismatch_innermapval_kptr", "bpf_spin_unlock of different lock" },
 	{ "lock_id_mismatch_innermapval_global", "bpf_spin_unlock of different lock" },
 	{ "lock_id_mismatch_innermapval_mapval", "bpf_spin_unlock of different lock" },
+	{ "lock_global_subprog_call1", "global function calls are not allowed while holding a lock" },
+	{ "lock_global_subprog_call2", "global function calls are not allowed while holding a lock" },
 };
 
 static int match_regex(const char *pattern, const char *string)
diff --git a/tools/testing/selftests/bpf/prog_tests/struct_ops_autocreate.c b/tools/testing/selftests/bpf/prog_tests/struct_ops_autocreate.c
new file mode 100644
index 0000000000..a5cc593c1e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/struct_ops_autocreate.c
@@ -0,0 +1,159 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "struct_ops_autocreate.skel.h"
+#include "struct_ops_autocreate2.skel.h"
+
+static void cant_load_full_object(void)
+{
+	struct struct_ops_autocreate *skel;
+	char *log = NULL;
+	int err;
+
+	skel = struct_ops_autocreate__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_autocreate__open"))
+		return;
+
+	if (start_libbpf_log_capture())
+		goto cleanup;
+	/* The testmod_2 map BTF type (struct bpf_testmod_ops___v2) doesn't
+	 * match the BTF of the actual struct bpf_testmod_ops defined in the
+	 * kernel, so we should fail to load it if we don't disable autocreate
+	 * for that map.
+	 */
+	err = struct_ops_autocreate__load(skel);
+	log = stop_libbpf_log_capture();
+	if (!ASSERT_ERR(err, "struct_ops_autocreate__load"))
+		goto cleanup;
+
+	ASSERT_HAS_SUBSTR(log, "libbpf: struct_ops init_kern", "init_kern message");
+	ASSERT_EQ(err, -ENOTSUP, "errno should be ENOTSUP");
+
+cleanup:
+	free(log);
+	struct_ops_autocreate__destroy(skel);
+}
+
+static int check_test_1_link(struct struct_ops_autocreate *skel, struct bpf_map *map)
+{
+	struct bpf_link *link;
+	int err;
+
+	link = bpf_map__attach_struct_ops(skel->maps.testmod_1);
+	if (!ASSERT_OK_PTR(link, "bpf_map__attach_struct_ops"))
+		return -1;
+
+	/* test_1() would be called from bpf_dummy_reg2() in bpf_testmod.c */
+	err = ASSERT_EQ(skel->bss->test_1_result, 42, "test_1_result");
+	bpf_link__destroy(link);
+	return err;
+}
+
+static void can_load_partial_object(void)
+{
+	struct struct_ops_autocreate *skel;
+	int err;
+
+	skel = struct_ops_autocreate__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_autocreate__open_opts"))
+		return;
+
+	err = bpf_map__set_autocreate(skel->maps.testmod_2, false);
+	if (!ASSERT_OK(err, "bpf_map__set_autocreate"))
+		goto cleanup;
+
+	ASSERT_TRUE(bpf_program__autoload(skel->progs.test_1), "test_1 default autoload");
+	ASSERT_TRUE(bpf_program__autoload(skel->progs.test_2), "test_2 default autoload");
+
+	err = struct_ops_autocreate__load(skel);
+	if (ASSERT_OK(err, "struct_ops_autocreate__load"))
+		goto cleanup;
+
+	ASSERT_TRUE(bpf_program__autoload(skel->progs.test_1), "test_1 actual autoload");
+	ASSERT_FALSE(bpf_program__autoload(skel->progs.test_2), "test_2 actual autoload");
+
+	check_test_1_link(skel, skel->maps.testmod_1);
+
+cleanup:
+	struct_ops_autocreate__destroy(skel);
+}
+
+static void optional_maps(void)
+{
+	struct struct_ops_autocreate *skel;
+	int err;
+
+	skel = struct_ops_autocreate__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_autocreate__open"))
+		return;
+
+	ASSERT_TRUE(bpf_map__autocreate(skel->maps.testmod_1), "testmod_1 autocreate");
+	ASSERT_TRUE(bpf_map__autocreate(skel->maps.testmod_2), "testmod_2 autocreate");
+	ASSERT_FALSE(bpf_map__autocreate(skel->maps.optional_map), "optional_map autocreate");
+	ASSERT_FALSE(bpf_map__autocreate(skel->maps.optional_map2), "optional_map2 autocreate");
+
+	err  = bpf_map__set_autocreate(skel->maps.testmod_1, false);
+	err |= bpf_map__set_autocreate(skel->maps.testmod_2, false);
+	err |= bpf_map__set_autocreate(skel->maps.optional_map2, true);
+	if (!ASSERT_OK(err, "bpf_map__set_autocreate"))
+		goto cleanup;
+
+	err = struct_ops_autocreate__load(skel);
+	if (ASSERT_OK(err, "struct_ops_autocreate__load"))
+		goto cleanup;
+
+	check_test_1_link(skel, skel->maps.optional_map2);
+
+cleanup:
+	struct_ops_autocreate__destroy(skel);
+}
+
+/* Swap test_mod1->test_1 program from 'bar' to 'foo' using shadow vars.
+ * test_mod1 load should enable autoload for 'foo'.
+ */
+static void autoload_and_shadow_vars(void)
+{
+	struct struct_ops_autocreate2 *skel = NULL;
+	struct bpf_link *link = NULL;
+	int err;
+
+	skel = struct_ops_autocreate2__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_autocreate__open_opts"))
+		return;
+
+	ASSERT_FALSE(bpf_program__autoload(skel->progs.foo), "foo default autoload");
+	ASSERT_FALSE(bpf_program__autoload(skel->progs.bar), "bar default autoload");
+
+	/* loading map testmod_1 would switch foo's autoload to true */
+	skel->struct_ops.testmod_1->test_1 = skel->progs.foo;
+
+	err = struct_ops_autocreate2__load(skel);
+	if (ASSERT_OK(err, "struct_ops_autocreate__load"))
+		goto cleanup;
+
+	ASSERT_TRUE(bpf_program__autoload(skel->progs.foo), "foo actual autoload");
+	ASSERT_FALSE(bpf_program__autoload(skel->progs.bar), "bar actual autoload");
+
+	link = bpf_map__attach_struct_ops(skel->maps.testmod_1);
+	if (!ASSERT_OK_PTR(link, "bpf_map__attach_struct_ops"))
+		goto cleanup;
+
+	/* test_1() would be called from bpf_dummy_reg2() in bpf_testmod.c */
+	err = ASSERT_EQ(skel->bss->test_1_result, 42, "test_1_result");
+
+cleanup:
+	bpf_link__destroy(link);
+	struct_ops_autocreate2__destroy(skel);
+}
+
+void test_struct_ops_autocreate(void)
+{
+	if (test__start_subtest("cant_load_full_object"))
+		cant_load_full_object();
+	if (test__start_subtest("can_load_partial_object"))
+		can_load_partial_object();
+	if (test__start_subtest("autoload_and_shadow_vars"))
+		autoload_and_shadow_vars();
+	if (test__start_subtest("optional_maps"))
+		optional_maps();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
index ea8537c544..c33c05161a 100644
--- a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
+++ b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
@@ -117,12 +117,6 @@ static void test_recursion(void)
 	ASSERT_OK(err, "lookup map_b");
 	ASSERT_EQ(value, 100, "map_b value");
 
-	prog_fd = bpf_program__fd(skel->progs.on_lookup);
-	memset(&info, 0, sizeof(info));
-	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
-	ASSERT_OK(err, "get prog info");
-	ASSERT_GT(info.recursion_misses, 0, "on_lookup prog recursion");
-
 	prog_fd = bpf_program__fd(skel->progs.on_update);
 	memset(&info, 0, sizeof(info));
 	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_custom_syncookie.c b/tools/testing/selftests/bpf/prog_tests/tcp_custom_syncookie.c
new file mode 100644
index 0000000000..eaf441dc7e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_custom_syncookie.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdlib.h>
+#include <net/if.h>
+
+#include "test_progs.h"
+#include "cgroup_helpers.h"
+#include "network_helpers.h"
+#include "test_tcp_custom_syncookie.skel.h"
+
+static struct test_tcp_custom_syncookie_case {
+	int family, type;
+	char addr[16];
+	char name[10];
+} test_cases[] = {
+	{
+		.name = "IPv4 TCP",
+		.family = AF_INET,
+		.type = SOCK_STREAM,
+		.addr = "127.0.0.1",
+	},
+	{
+		.name = "IPv6 TCP",
+		.family = AF_INET6,
+		.type = SOCK_STREAM,
+		.addr = "::1",
+	},
+};
+
+static int setup_netns(void)
+{
+	if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns"))
+		return -1;
+
+	if (!ASSERT_OK(system("ip link set dev lo up"), "ip"))
+		goto err;
+
+	if (!ASSERT_OK(write_sysctl("/proc/sys/net/ipv4/tcp_ecn", "1"),
+		       "write_sysctl"))
+		goto err;
+
+	return 0;
+err:
+	return -1;
+}
+
+static int setup_tc(struct test_tcp_custom_syncookie *skel)
+{
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_lo, .attach_point = BPF_TC_INGRESS);
+	LIBBPF_OPTS(bpf_tc_opts, tc_attach,
+		    .prog_fd = bpf_program__fd(skel->progs.tcp_custom_syncookie));
+
+	qdisc_lo.ifindex = if_nametoindex("lo");
+	if (!ASSERT_OK(bpf_tc_hook_create(&qdisc_lo), "qdisc add dev lo clsact"))
+		goto err;
+
+	if (!ASSERT_OK(bpf_tc_attach(&qdisc_lo, &tc_attach),
+		       "filter add dev lo ingress"))
+		goto err;
+
+	return 0;
+err:
+	return -1;
+}
+
+#define msg "Hello World"
+#define msglen 11
+
+static void transfer_message(int sender, int receiver)
+{
+	char buf[msglen];
+	int ret;
+
+	ret = send(sender, msg, msglen, 0);
+	if (!ASSERT_EQ(ret, msglen, "send"))
+		return;
+
+	memset(buf, 0, sizeof(buf));
+
+	ret = recv(receiver, buf, msglen, 0);
+	if (!ASSERT_EQ(ret, msglen, "recv"))
+		return;
+
+	ret = strncmp(buf, msg, msglen);
+	if (!ASSERT_EQ(ret, 0, "strncmp"))
+		return;
+}
+
+static void create_connection(struct test_tcp_custom_syncookie_case *test_case)
+{
+	int server, client, child;
+
+	server = start_server(test_case->family, test_case->type, test_case->addr, 0, 0);
+	if (!ASSERT_NEQ(server, -1, "start_server"))
+		return;
+
+	client = connect_to_fd(server, 0);
+	if (!ASSERT_NEQ(client, -1, "connect_to_fd"))
+		goto close_server;
+
+	child = accept(server, NULL, 0);
+	if (!ASSERT_NEQ(child, -1, "accept"))
+		goto close_client;
+
+	transfer_message(client, child);
+	transfer_message(child, client);
+
+	close(child);
+close_client:
+	close(client);
+close_server:
+	close(server);
+}
+
+void test_tcp_custom_syncookie(void)
+{
+	struct test_tcp_custom_syncookie *skel;
+	int i;
+
+	if (setup_netns())
+		return;
+
+	skel = test_tcp_custom_syncookie__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	if (setup_tc(skel))
+		goto destroy_skel;
+
+	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
+		if (!test__start_subtest(test_cases[i].name))
+			continue;
+
+		skel->bss->handled_syn = false;
+		skel->bss->handled_ack = false;
+
+		create_connection(&test_cases[i]);
+
+		ASSERT_EQ(skel->bss->handled_syn, true, "SYN is not handled at tc.");
+		ASSERT_EQ(skel->bss->handled_ack, true, "ACK is not handled at tc");
+	}
+
+destroy_skel:
+	system("tc qdisc del dev lo clsact");
+
+	test_tcp_custom_syncookie__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_maybe_null.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_maybe_null.c
new file mode 100644
index 0000000000..01dc2613c8
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_maybe_null.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+
+#include "struct_ops_maybe_null.skel.h"
+#include "struct_ops_maybe_null_fail.skel.h"
+
+/* Test that the verifier accepts a program that access a nullable pointer
+ * with a proper check.
+ */
+static void maybe_null(void)
+{
+	struct struct_ops_maybe_null *skel;
+
+	skel = struct_ops_maybe_null__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_module_open_and_load"))
+		return;
+
+	struct_ops_maybe_null__destroy(skel);
+}
+
+/* Test that the verifier rejects a program that access a nullable pointer
+ * without a check beforehand.
+ */
+static void maybe_null_fail(void)
+{
+	struct struct_ops_maybe_null_fail *skel;
+
+	skel = struct_ops_maybe_null_fail__open_and_load();
+	if (ASSERT_ERR_PTR(skel, "struct_ops_module_fail__open_and_load"))
+		return;
+
+	struct_ops_maybe_null_fail__destroy(skel);
+}
+
+void test_struct_ops_maybe_null(void)
+{
+	/* The verifier verifies the programs at load time, so testing both
+	 * programs in the same compile-unit is complicated. We run them in
+	 * separate objects to simplify the testing.
+	 */
+	if (test__start_subtest("maybe_null"))
+		maybe_null();
+	if (test__start_subtest("maybe_null_fail"))
+		maybe_null_fail();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c
new file mode 100644
index 0000000000..ee5372c7f2
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <time.h>
+
+#include "struct_ops_module.skel.h"
+
+static void check_map_info(struct bpf_map_info *info)
+{
+	struct bpf_btf_info btf_info;
+	char btf_name[256];
+	u32 btf_info_len = sizeof(btf_info);
+	int err, fd;
+
+	fd = bpf_btf_get_fd_by_id(info->btf_vmlinux_id);
+	if (!ASSERT_GE(fd, 0, "get_value_type_btf_obj_fd"))
+		return;
+
+	memset(&btf_info, 0, sizeof(btf_info));
+	btf_info.name = ptr_to_u64(btf_name);
+	btf_info.name_len = sizeof(btf_name);
+	err = bpf_btf_get_info_by_fd(fd, &btf_info, &btf_info_len);
+	if (!ASSERT_OK(err, "get_value_type_btf_obj_info"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(strcmp(btf_name, "bpf_testmod"), 0, "get_value_type_btf_obj_name"))
+		goto cleanup;
+
+cleanup:
+	close(fd);
+}
+
+static int attach_ops_and_check(struct struct_ops_module *skel,
+				struct bpf_map *map,
+				int expected_test_2_result)
+{
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(map);
+	ASSERT_OK_PTR(link, "attach_test_mod_1");
+	if (!link)
+		return -1;
+
+	/* test_{1,2}() would be called from bpf_dummy_reg() in bpf_testmod.c */
+	ASSERT_EQ(skel->bss->test_1_result, 0xdeadbeef, "test_1_result");
+	ASSERT_EQ(skel->bss->test_2_result, expected_test_2_result, "test_2_result");
+
+	bpf_link__destroy(link);
+	return 0;
+}
+
+static void test_struct_ops_load(void)
+{
+	struct struct_ops_module *skel;
+	struct bpf_map_info info = {};
+	int err;
+	u32 len;
+
+	skel = struct_ops_module__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_module_open"))
+		return;
+
+	skel->struct_ops.testmod_1->data = 13;
+	skel->struct_ops.testmod_1->test_2 = skel->progs.test_3;
+	/* Since test_2() is not being used, it should be disabled from
+	 * auto-loading, or it will fail to load.
+	 */
+	bpf_program__set_autoload(skel->progs.test_2, false);
+
+	err = struct_ops_module__load(skel);
+	if (!ASSERT_OK(err, "struct_ops_module_load"))
+		goto cleanup;
+
+	len = sizeof(info);
+	err = bpf_map_get_info_by_fd(bpf_map__fd(skel->maps.testmod_1), &info,
+				     &len);
+	if (!ASSERT_OK(err, "bpf_map_get_info_by_fd"))
+		goto cleanup;
+
+	check_map_info(&info);
+	/* test_3() will be called from bpf_dummy_reg() in bpf_testmod.c
+	 *
+	 * In bpf_testmod.c it will pass 4 and 13 (the value of data) to
+	 * .test_2.  So, the value of test_2_result should be 20 (4 + 13 +
+	 * 3).
+	 */
+	if (!attach_ops_and_check(skel, skel->maps.testmod_1, 20))
+		goto cleanup;
+	if (!attach_ops_and_check(skel, skel->maps.testmod_2, 12))
+		goto cleanup;
+
+cleanup:
+	struct_ops_module__destroy(skel);
+}
+
+void serial_test_struct_ops_module(void)
+{
+	if (test__start_subtest("test_struct_ops_load"))
+		test_struct_ops_load();
+}
+
diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_multi_pages.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_multi_pages.c
new file mode 100644
index 0000000000..645d32b516
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_multi_pages.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+
+#include "struct_ops_multi_pages.skel.h"
+
+static void do_struct_ops_multi_pages(void)
+{
+	struct struct_ops_multi_pages *skel;
+	struct bpf_link *link;
+
+	/* The size of all trampolines of skel->maps.multi_pages should be
+	 * over 1 page (at least for x86).
+	 */
+	skel = struct_ops_multi_pages__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_multi_pages_open_and_load"))
+		return;
+
+	link = bpf_map__attach_struct_ops(skel->maps.multi_pages);
+	ASSERT_OK_PTR(link, "attach_multi_pages");
+
+	bpf_link__destroy(link);
+	struct_ops_multi_pages__destroy(skel);
+}
+
+void test_struct_ops_multi_pages(void)
+{
+	if (test__start_subtest("multi_pages"))
+		do_struct_ops_multi_pages();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_no_cfi.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_no_cfi.c
new file mode 100644
index 0000000000..106ea44796
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_no_cfi.c
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <testing_helpers.h>
+
+static void load_bpf_test_no_cfi(void)
+{
+	int fd;
+	int err;
+
+	fd = open("bpf_test_no_cfi.ko", O_RDONLY);
+	if (!ASSERT_GE(fd, 0, "open"))
+		return;
+
+	/* The module will try to register a struct_ops type without
+	 * cfi_stubs and with cfi_stubs.
+	 *
+	 * The one without cfi_stub should fail. The module will be loaded
+	 * successfully only if the result of the registration is as
+	 * expected, or it fails.
+	 */
+	err = finit_module(fd, "", 0);
+	close(fd);
+	if (!ASSERT_OK(err, "finit_module"))
+		return;
+
+	err = delete_module("bpf_test_no_cfi", 0);
+	ASSERT_OK(err, "delete_module");
+}
+
+void test_struct_ops_no_cfi(void)
+{
+	if (test__start_subtest("load_bpf_test_no_cfi"))
+		load_bpf_test_no_cfi();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
index 2b3c6dd662..5f1fb0a2ea 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
@@ -118,9 +118,9 @@ fail:
 static void cleanup(void)
 {
 	SYS_NOFAIL("test -f /var/run/netns/at_ns0 && ip netns delete at_ns0");
-	SYS_NOFAIL("ip link del veth1 2> /dev/null");
-	SYS_NOFAIL("ip link del %s 2> /dev/null", VXLAN_TUNL_DEV1);
-	SYS_NOFAIL("ip link del %s 2> /dev/null", IP6VXLAN_TUNL_DEV1);
+	SYS_NOFAIL("ip link del veth1");
+	SYS_NOFAIL("ip link del %s", VXLAN_TUNL_DEV1);
+	SYS_NOFAIL("ip link del %s", IP6VXLAN_TUNL_DEV1);
 }
 
 static int add_vxlan_tunnel(void)
@@ -265,9 +265,9 @@ fail:
 static void delete_ipip_tunnel(void)
 {
 	SYS_NOFAIL("ip -n at_ns0 link delete dev %s", IPIP_TUNL_DEV0);
-	SYS_NOFAIL("ip -n at_ns0 fou del port 5555 2> /dev/null");
+	SYS_NOFAIL("ip -n at_ns0 fou del port 5555");
 	SYS_NOFAIL("ip link delete dev %s", IPIP_TUNL_DEV1);
-	SYS_NOFAIL("ip fou del port 5555 2> /dev/null");
+	SYS_NOFAIL("ip fou del port 5555");
 }
 
 static int add_xfrm_tunnel(void)
@@ -346,13 +346,13 @@ fail:
 
 static void delete_xfrm_tunnel(void)
 {
-	SYS_NOFAIL("ip xfrm policy delete dir out src %s/32 dst %s/32 2> /dev/null",
+	SYS_NOFAIL("ip xfrm policy delete dir out src %s/32 dst %s/32",
 		   IP4_ADDR_TUNL_DEV1, IP4_ADDR_TUNL_DEV0);
-	SYS_NOFAIL("ip xfrm policy delete dir in src %s/32 dst %s/32 2> /dev/null",
+	SYS_NOFAIL("ip xfrm policy delete dir in src %s/32 dst %s/32",
 		   IP4_ADDR_TUNL_DEV0, IP4_ADDR_TUNL_DEV1);
-	SYS_NOFAIL("ip xfrm state delete src %s dst %s proto esp spi %d 2> /dev/null",
+	SYS_NOFAIL("ip xfrm state delete src %s dst %s proto esp spi %d",
 		   IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT);
-	SYS_NOFAIL("ip xfrm state delete src %s dst %s proto esp spi %d 2> /dev/null",
+	SYS_NOFAIL("ip xfrm state delete src %s dst %s proto esp spi %d",
 		   IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN);
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/token.c b/tools/testing/selftests/bpf/prog_tests/token.c
new file mode 100644
index 0000000000..fc4a175d8d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/token.c
@@ -0,0 +1,1052 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+#define _GNU_SOURCE
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include "cap_helpers.h"
+#include <fcntl.h>
+#include <sched.h>
+#include <signal.h>
+#include <unistd.h>
+#include <linux/filter.h>
+#include <linux/unistd.h>
+#include <linux/mount.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/un.h>
+#include "priv_map.skel.h"
+#include "priv_prog.skel.h"
+#include "dummy_st_ops_success.skel.h"
+#include "token_lsm.skel.h"
+
+static inline int sys_mount(const char *dev_name, const char *dir_name,
+			    const char *type, unsigned long flags,
+			    const void *data)
+{
+	return syscall(__NR_mount, dev_name, dir_name, type, flags, data);
+}
+
+static inline int sys_fsopen(const char *fsname, unsigned flags)
+{
+	return syscall(__NR_fsopen, fsname, flags);
+}
+
+static inline int sys_fspick(int dfd, const char *path, unsigned flags)
+{
+	return syscall(__NR_fspick, dfd, path, flags);
+}
+
+static inline int sys_fsconfig(int fs_fd, unsigned cmd, const char *key, const void *val, int aux)
+{
+	return syscall(__NR_fsconfig, fs_fd, cmd, key, val, aux);
+}
+
+static inline int sys_fsmount(int fs_fd, unsigned flags, unsigned ms_flags)
+{
+	return syscall(__NR_fsmount, fs_fd, flags, ms_flags);
+}
+
+static inline int sys_move_mount(int from_dfd, const char *from_path,
+				 int to_dfd, const char *to_path,
+				 unsigned flags)
+{
+	return syscall(__NR_move_mount, from_dfd, from_path, to_dfd, to_path, flags);
+}
+
+static int drop_priv_caps(__u64 *old_caps)
+{
+	return cap_disable_effective((1ULL << CAP_BPF) |
+				     (1ULL << CAP_PERFMON) |
+				     (1ULL << CAP_NET_ADMIN) |
+				     (1ULL << CAP_SYS_ADMIN), old_caps);
+}
+
+static int restore_priv_caps(__u64 old_caps)
+{
+	return cap_enable_effective(old_caps, NULL);
+}
+
+static int set_delegate_mask(int fs_fd, const char *key, __u64 mask, const char *mask_str)
+{
+	char buf[32];
+	int err;
+
+	if (!mask_str) {
+		if (mask == ~0ULL) {
+			mask_str = "any";
+		} else {
+			snprintf(buf, sizeof(buf), "0x%llx", (unsigned long long)mask);
+			mask_str = buf;
+		}
+	}
+
+	err = sys_fsconfig(fs_fd, FSCONFIG_SET_STRING, key,
+			   mask_str, 0);
+	if (err < 0)
+		err = -errno;
+	return err;
+}
+
+#define zclose(fd) do { if (fd >= 0) close(fd); fd = -1; } while (0)
+
+struct bpffs_opts {
+	__u64 cmds;
+	__u64 maps;
+	__u64 progs;
+	__u64 attachs;
+	const char *cmds_str;
+	const char *maps_str;
+	const char *progs_str;
+	const char *attachs_str;
+};
+
+static int create_bpffs_fd(void)
+{
+	int fs_fd;
+
+	/* create VFS context */
+	fs_fd = sys_fsopen("bpf", 0);
+	ASSERT_GE(fs_fd, 0, "fs_fd");
+
+	return fs_fd;
+}
+
+static int materialize_bpffs_fd(int fs_fd, struct bpffs_opts *opts)
+{
+	int mnt_fd, err;
+
+	/* set up token delegation mount options */
+	err = set_delegate_mask(fs_fd, "delegate_cmds", opts->cmds, opts->cmds_str);
+	if (!ASSERT_OK(err, "fs_cfg_cmds"))
+		return err;
+	err = set_delegate_mask(fs_fd, "delegate_maps", opts->maps, opts->maps_str);
+	if (!ASSERT_OK(err, "fs_cfg_maps"))
+		return err;
+	err = set_delegate_mask(fs_fd, "delegate_progs", opts->progs, opts->progs_str);
+	if (!ASSERT_OK(err, "fs_cfg_progs"))
+		return err;
+	err = set_delegate_mask(fs_fd, "delegate_attachs", opts->attachs, opts->attachs_str);
+	if (!ASSERT_OK(err, "fs_cfg_attachs"))
+		return err;
+
+	/* instantiate FS object */
+	err = sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0);
+	if (err < 0)
+		return -errno;
+
+	/* create O_PATH fd for detached mount */
+	mnt_fd = sys_fsmount(fs_fd, 0, 0);
+	if (err < 0)
+		return -errno;
+
+	return mnt_fd;
+}
+
+/* send FD over Unix domain (AF_UNIX) socket */
+static int sendfd(int sockfd, int fd)
+{
+	struct msghdr msg = {};
+	struct cmsghdr *cmsg;
+	int fds[1] = { fd }, err;
+	char iobuf[1];
+	struct iovec io = {
+		.iov_base = iobuf,
+		.iov_len = sizeof(iobuf),
+	};
+	union {
+		char buf[CMSG_SPACE(sizeof(fds))];
+		struct cmsghdr align;
+	} u;
+
+	msg.msg_iov = &io;
+	msg.msg_iovlen = 1;
+	msg.msg_control = u.buf;
+	msg.msg_controllen = sizeof(u.buf);
+	cmsg = CMSG_FIRSTHDR(&msg);
+	cmsg->cmsg_level = SOL_SOCKET;
+	cmsg->cmsg_type = SCM_RIGHTS;
+	cmsg->cmsg_len = CMSG_LEN(sizeof(fds));
+	memcpy(CMSG_DATA(cmsg), fds, sizeof(fds));
+
+	err = sendmsg(sockfd, &msg, 0);
+	if (err < 0)
+		err = -errno;
+	if (!ASSERT_EQ(err, 1, "sendmsg"))
+		return -EINVAL;
+
+	return 0;
+}
+
+/* receive FD over Unix domain (AF_UNIX) socket */
+static int recvfd(int sockfd, int *fd)
+{
+	struct msghdr msg = {};
+	struct cmsghdr *cmsg;
+	int fds[1], err;
+	char iobuf[1];
+	struct iovec io = {
+		.iov_base = iobuf,
+		.iov_len = sizeof(iobuf),
+	};
+	union {
+		char buf[CMSG_SPACE(sizeof(fds))];
+		struct cmsghdr align;
+	} u;
+
+	msg.msg_iov = &io;
+	msg.msg_iovlen = 1;
+	msg.msg_control = u.buf;
+	msg.msg_controllen = sizeof(u.buf);
+
+	err = recvmsg(sockfd, &msg, 0);
+	if (err < 0)
+		err = -errno;
+	if (!ASSERT_EQ(err, 1, "recvmsg"))
+		return -EINVAL;
+
+	cmsg = CMSG_FIRSTHDR(&msg);
+	if (!ASSERT_OK_PTR(cmsg, "cmsg_null") ||
+	    !ASSERT_EQ(cmsg->cmsg_len, CMSG_LEN(sizeof(fds)), "cmsg_len") ||
+	    !ASSERT_EQ(cmsg->cmsg_level, SOL_SOCKET, "cmsg_level") ||
+	    !ASSERT_EQ(cmsg->cmsg_type, SCM_RIGHTS, "cmsg_type"))
+		return -EINVAL;
+
+	memcpy(fds, CMSG_DATA(cmsg), sizeof(fds));
+	*fd = fds[0];
+
+	return 0;
+}
+
+static ssize_t write_nointr(int fd, const void *buf, size_t count)
+{
+	ssize_t ret;
+
+	do {
+		ret = write(fd, buf, count);
+	} while (ret < 0 && errno == EINTR);
+
+	return ret;
+}
+
+static int write_file(const char *path, const void *buf, size_t count)
+{
+	int fd;
+	ssize_t ret;
+
+	fd = open(path, O_WRONLY | O_CLOEXEC | O_NOCTTY | O_NOFOLLOW);
+	if (fd < 0)
+		return -1;
+
+	ret = write_nointr(fd, buf, count);
+	close(fd);
+	if (ret < 0 || (size_t)ret != count)
+		return -1;
+
+	return 0;
+}
+
+static int create_and_enter_userns(void)
+{
+	uid_t uid;
+	gid_t gid;
+	char map[100];
+
+	uid = getuid();
+	gid = getgid();
+
+	if (unshare(CLONE_NEWUSER))
+		return -1;
+
+	if (write_file("/proc/self/setgroups", "deny", sizeof("deny") - 1) &&
+	    errno != ENOENT)
+		return -1;
+
+	snprintf(map, sizeof(map), "0 %d 1", uid);
+	if (write_file("/proc/self/uid_map", map, strlen(map)))
+		return -1;
+
+
+	snprintf(map, sizeof(map), "0 %d 1", gid);
+	if (write_file("/proc/self/gid_map", map, strlen(map)))
+		return -1;
+
+	if (setgid(0))
+		return -1;
+
+	if (setuid(0))
+		return -1;
+
+	return 0;
+}
+
+typedef int (*child_callback_fn)(int bpffs_fd, struct token_lsm *lsm_skel);
+
+static void child(int sock_fd, struct bpffs_opts *opts, child_callback_fn callback)
+{
+	int mnt_fd = -1, fs_fd = -1, err = 0, bpffs_fd = -1, token_fd = -1;
+	struct token_lsm *lsm_skel = NULL;
+
+	/* load and attach LSM "policy" before we go into unpriv userns */
+	lsm_skel = token_lsm__open_and_load();
+	if (!ASSERT_OK_PTR(lsm_skel, "lsm_skel_load")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+	lsm_skel->bss->my_pid = getpid();
+	err = token_lsm__attach(lsm_skel);
+	if (!ASSERT_OK(err, "lsm_skel_attach"))
+		goto cleanup;
+
+	/* setup userns with root mappings */
+	err = create_and_enter_userns();
+	if (!ASSERT_OK(err, "create_and_enter_userns"))
+		goto cleanup;
+
+	/* setup mountns to allow creating BPF FS (fsopen("bpf")) from unpriv process */
+	err = unshare(CLONE_NEWNS);
+	if (!ASSERT_OK(err, "create_mountns"))
+		goto cleanup;
+
+	err = sys_mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0);
+	if (!ASSERT_OK(err, "remount_root"))
+		goto cleanup;
+
+	fs_fd = create_bpffs_fd();
+	if (!ASSERT_GE(fs_fd, 0, "create_bpffs_fd")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* ensure unprivileged child cannot set delegation options */
+	err = set_delegate_mask(fs_fd, "delegate_cmds", 0x1, NULL);
+	ASSERT_EQ(err, -EPERM, "delegate_cmd_eperm");
+	err = set_delegate_mask(fs_fd, "delegate_maps", 0x1, NULL);
+	ASSERT_EQ(err, -EPERM, "delegate_maps_eperm");
+	err = set_delegate_mask(fs_fd, "delegate_progs", 0x1, NULL);
+	ASSERT_EQ(err, -EPERM, "delegate_progs_eperm");
+	err = set_delegate_mask(fs_fd, "delegate_attachs", 0x1, NULL);
+	ASSERT_EQ(err, -EPERM, "delegate_attachs_eperm");
+
+	/* pass BPF FS context object to parent */
+	err = sendfd(sock_fd, fs_fd);
+	if (!ASSERT_OK(err, "send_fs_fd"))
+		goto cleanup;
+	zclose(fs_fd);
+
+	/* avoid mucking around with mount namespaces and mounting at
+	 * well-known path, just get detach-mounted BPF FS fd back from parent
+	 */
+	err = recvfd(sock_fd, &mnt_fd);
+	if (!ASSERT_OK(err, "recv_mnt_fd"))
+		goto cleanup;
+
+	/* try to fspick() BPF FS and try to add some delegation options */
+	fs_fd = sys_fspick(mnt_fd, "", FSPICK_EMPTY_PATH);
+	if (!ASSERT_GE(fs_fd, 0, "bpffs_fspick")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* ensure unprivileged child cannot reconfigure to set delegation options */
+	err = set_delegate_mask(fs_fd, "delegate_cmds", 0, "any");
+	if (!ASSERT_EQ(err, -EPERM, "delegate_cmd_eperm_reconfig")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+	err = set_delegate_mask(fs_fd, "delegate_maps", 0, "any");
+	if (!ASSERT_EQ(err, -EPERM, "delegate_maps_eperm_reconfig")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+	err = set_delegate_mask(fs_fd, "delegate_progs", 0, "any");
+	if (!ASSERT_EQ(err, -EPERM, "delegate_progs_eperm_reconfig")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+	err = set_delegate_mask(fs_fd, "delegate_attachs", 0, "any");
+	if (!ASSERT_EQ(err, -EPERM, "delegate_attachs_eperm_reconfig")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+	zclose(fs_fd);
+
+	bpffs_fd = openat(mnt_fd, ".", 0, O_RDWR);
+	if (!ASSERT_GE(bpffs_fd, 0, "bpffs_open")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* create BPF token FD and pass it to parent for some extra checks */
+	token_fd = bpf_token_create(bpffs_fd, NULL);
+	if (!ASSERT_GT(token_fd, 0, "child_token_create")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+	err = sendfd(sock_fd, token_fd);
+	if (!ASSERT_OK(err, "send_token_fd"))
+		goto cleanup;
+	zclose(token_fd);
+
+	/* do custom test logic with customly set up BPF FS instance */
+	err = callback(bpffs_fd, lsm_skel);
+	if (!ASSERT_OK(err, "test_callback"))
+		goto cleanup;
+
+	err = 0;
+cleanup:
+	zclose(sock_fd);
+	zclose(mnt_fd);
+	zclose(fs_fd);
+	zclose(bpffs_fd);
+	zclose(token_fd);
+
+	lsm_skel->bss->my_pid = 0;
+	token_lsm__destroy(lsm_skel);
+
+	exit(-err);
+}
+
+static int wait_for_pid(pid_t pid)
+{
+	int status, ret;
+
+again:
+	ret = waitpid(pid, &status, 0);
+	if (ret == -1) {
+		if (errno == EINTR)
+			goto again;
+
+		return -1;
+	}
+
+	if (!WIFEXITED(status))
+		return -1;
+
+	return WEXITSTATUS(status);
+}
+
+static void parent(int child_pid, struct bpffs_opts *bpffs_opts, int sock_fd)
+{
+	int fs_fd = -1, mnt_fd = -1, token_fd = -1, err;
+
+	err = recvfd(sock_fd, &fs_fd);
+	if (!ASSERT_OK(err, "recv_bpffs_fd"))
+		goto cleanup;
+
+	mnt_fd = materialize_bpffs_fd(fs_fd, bpffs_opts);
+	if (!ASSERT_GE(mnt_fd, 0, "materialize_bpffs_fd")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+	zclose(fs_fd);
+
+	/* pass BPF FS context object to parent */
+	err = sendfd(sock_fd, mnt_fd);
+	if (!ASSERT_OK(err, "send_mnt_fd"))
+		goto cleanup;
+	zclose(mnt_fd);
+
+	/* receive BPF token FD back from child for some extra tests */
+	err = recvfd(sock_fd, &token_fd);
+	if (!ASSERT_OK(err, "recv_token_fd"))
+		goto cleanup;
+
+	err = wait_for_pid(child_pid);
+	ASSERT_OK(err, "waitpid_child");
+
+cleanup:
+	zclose(sock_fd);
+	zclose(fs_fd);
+	zclose(mnt_fd);
+	zclose(token_fd);
+
+	if (child_pid > 0)
+		(void)kill(child_pid, SIGKILL);
+}
+
+static void subtest_userns(struct bpffs_opts *bpffs_opts,
+			   child_callback_fn child_cb)
+{
+	int sock_fds[2] = { -1, -1 };
+	int child_pid = 0, err;
+
+	err = socketpair(AF_UNIX, SOCK_STREAM, 0, sock_fds);
+	if (!ASSERT_OK(err, "socketpair"))
+		goto cleanup;
+
+	child_pid = fork();
+	if (!ASSERT_GE(child_pid, 0, "fork"))
+		goto cleanup;
+
+	if (child_pid == 0) {
+		zclose(sock_fds[0]);
+		return child(sock_fds[1], bpffs_opts, child_cb);
+
+	} else {
+		zclose(sock_fds[1]);
+		return parent(child_pid, bpffs_opts, sock_fds[0]);
+	}
+
+cleanup:
+	zclose(sock_fds[0]);
+	zclose(sock_fds[1]);
+	if (child_pid > 0)
+		(void)kill(child_pid, SIGKILL);
+}
+
+static int userns_map_create(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts);
+	int err, token_fd = -1, map_fd = -1;
+	__u64 old_caps = 0;
+
+	/* create BPF token from BPF FS mount */
+	token_fd = bpf_token_create(mnt_fd, NULL);
+	if (!ASSERT_GT(token_fd, 0, "token_create")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* while inside non-init userns, we need both a BPF token *and*
+	 * CAP_BPF inside current userns to create privileged map; let's test
+	 * that neither BPF token alone nor namespaced CAP_BPF is sufficient
+	 */
+	err = drop_priv_caps(&old_caps);
+	if (!ASSERT_OK(err, "drop_caps"))
+		goto cleanup;
+
+	/* no token, no CAP_BPF -> fail */
+	map_opts.map_flags = 0;
+	map_opts.token_fd = 0;
+	map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "wo_token_wo_bpf", 0, 8, 1, &map_opts);
+	if (!ASSERT_LT(map_fd, 0, "stack_map_wo_token_wo_cap_bpf_should_fail")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* token without CAP_BPF -> fail */
+	map_opts.map_flags = BPF_F_TOKEN_FD;
+	map_opts.token_fd = token_fd;
+	map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "w_token_wo_bpf", 0, 8, 1, &map_opts);
+	if (!ASSERT_LT(map_fd, 0, "stack_map_w_token_wo_cap_bpf_should_fail")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* get back effective local CAP_BPF (and CAP_SYS_ADMIN) */
+	err = restore_priv_caps(old_caps);
+	if (!ASSERT_OK(err, "restore_caps"))
+		goto cleanup;
+
+	/* CAP_BPF without token -> fail */
+	map_opts.map_flags = 0;
+	map_opts.token_fd = 0;
+	map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "wo_token_w_bpf", 0, 8, 1, &map_opts);
+	if (!ASSERT_LT(map_fd, 0, "stack_map_wo_token_w_cap_bpf_should_fail")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* finally, namespaced CAP_BPF + token -> success */
+	map_opts.map_flags = BPF_F_TOKEN_FD;
+	map_opts.token_fd = token_fd;
+	map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "w_token_w_bpf", 0, 8, 1, &map_opts);
+	if (!ASSERT_GT(map_fd, 0, "stack_map_w_token_w_cap_bpf")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+cleanup:
+	zclose(token_fd);
+	zclose(map_fd);
+	return err;
+}
+
+static int userns_btf_load(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	LIBBPF_OPTS(bpf_btf_load_opts, btf_opts);
+	int err, token_fd = -1, btf_fd = -1;
+	const void *raw_btf_data;
+	struct btf *btf = NULL;
+	__u32 raw_btf_size;
+	__u64 old_caps = 0;
+
+	/* create BPF token from BPF FS mount */
+	token_fd = bpf_token_create(mnt_fd, NULL);
+	if (!ASSERT_GT(token_fd, 0, "token_create")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* while inside non-init userns, we need both a BPF token *and*
+	 * CAP_BPF inside current userns to create privileged map; let's test
+	 * that neither BPF token alone nor namespaced CAP_BPF is sufficient
+	 */
+	err = drop_priv_caps(&old_caps);
+	if (!ASSERT_OK(err, "drop_caps"))
+		goto cleanup;
+
+	/* setup a trivial BTF data to load to the kernel */
+	btf = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf, "empty_btf"))
+		goto cleanup;
+
+	ASSERT_GT(btf__add_int(btf, "int", 4, 0), 0, "int_type");
+
+	raw_btf_data = btf__raw_data(btf, &raw_btf_size);
+	if (!ASSERT_OK_PTR(raw_btf_data, "raw_btf_data"))
+		goto cleanup;
+
+	/* no token + no CAP_BPF -> failure */
+	btf_opts.btf_flags = 0;
+	btf_opts.token_fd = 0;
+	btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts);
+	if (!ASSERT_LT(btf_fd, 0, "no_token_no_cap_should_fail"))
+		goto cleanup;
+
+	/* token + no CAP_BPF -> failure */
+	btf_opts.btf_flags = BPF_F_TOKEN_FD;
+	btf_opts.token_fd = token_fd;
+	btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts);
+	if (!ASSERT_LT(btf_fd, 0, "token_no_cap_should_fail"))
+		goto cleanup;
+
+	/* get back effective local CAP_BPF (and CAP_SYS_ADMIN) */
+	err = restore_priv_caps(old_caps);
+	if (!ASSERT_OK(err, "restore_caps"))
+		goto cleanup;
+
+	/* token + CAP_BPF -> success */
+	btf_opts.btf_flags = BPF_F_TOKEN_FD;
+	btf_opts.token_fd = token_fd;
+	btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts);
+	if (!ASSERT_GT(btf_fd, 0, "token_and_cap_success"))
+		goto cleanup;
+
+	err = 0;
+cleanup:
+	btf__free(btf);
+	zclose(btf_fd);
+	zclose(token_fd);
+	return err;
+}
+
+static int userns_prog_load(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, prog_opts);
+	int err, token_fd = -1, prog_fd = -1;
+	struct bpf_insn insns[] = {
+		/* bpf_jiffies64() requires CAP_BPF */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_jiffies64),
+		/* bpf_get_current_task() requires CAP_PERFMON */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_current_task),
+		/* r0 = 0; exit; */
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	size_t insn_cnt = ARRAY_SIZE(insns);
+	__u64 old_caps = 0;
+
+	/* create BPF token from BPF FS mount */
+	token_fd = bpf_token_create(mnt_fd, NULL);
+	if (!ASSERT_GT(token_fd, 0, "token_create")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* validate we can successfully load BPF program with token; this
+	 * being XDP program (CAP_NET_ADMIN) using bpf_jiffies64() (CAP_BPF)
+	 * and bpf_get_current_task() (CAP_PERFMON) helpers validates we have
+	 * BPF token wired properly in a bunch of places in the kernel
+	 */
+	prog_opts.prog_flags = BPF_F_TOKEN_FD;
+	prog_opts.token_fd = token_fd;
+	prog_opts.expected_attach_type = BPF_XDP;
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL",
+				insns, insn_cnt, &prog_opts);
+	if (!ASSERT_GT(prog_fd, 0, "prog_fd")) {
+		err = -EPERM;
+		goto cleanup;
+	}
+
+	/* no token + caps -> failure */
+	prog_opts.prog_flags = 0;
+	prog_opts.token_fd = 0;
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL",
+				insns, insn_cnt, &prog_opts);
+	if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) {
+		err = -EPERM;
+		goto cleanup;
+	}
+
+	err = drop_priv_caps(&old_caps);
+	if (!ASSERT_OK(err, "drop_caps"))
+		goto cleanup;
+
+	/* no caps + token -> failure */
+	prog_opts.prog_flags = BPF_F_TOKEN_FD;
+	prog_opts.token_fd = token_fd;
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL",
+				insns, insn_cnt, &prog_opts);
+	if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) {
+		err = -EPERM;
+		goto cleanup;
+	}
+
+	/* no caps + no token -> definitely a failure */
+	prog_opts.prog_flags = 0;
+	prog_opts.token_fd = 0;
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL",
+				insns, insn_cnt, &prog_opts);
+	if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) {
+		err = -EPERM;
+		goto cleanup;
+	}
+
+	err = 0;
+cleanup:
+	zclose(prog_fd);
+	zclose(token_fd);
+	return err;
+}
+
+static int userns_obj_priv_map(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	LIBBPF_OPTS(bpf_object_open_opts, opts);
+	char buf[256];
+	struct priv_map *skel;
+	int err;
+
+	skel = priv_map__open_and_load();
+	if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) {
+		priv_map__destroy(skel);
+		return -EINVAL;
+	}
+
+	/* use bpf_token_path to provide BPF FS path */
+	snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd);
+	opts.bpf_token_path = buf;
+	skel = priv_map__open_opts(&opts);
+	if (!ASSERT_OK_PTR(skel, "obj_token_path_open"))
+		return -EINVAL;
+
+	err = priv_map__load(skel);
+	priv_map__destroy(skel);
+	if (!ASSERT_OK(err, "obj_token_path_load"))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int userns_obj_priv_prog(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	LIBBPF_OPTS(bpf_object_open_opts, opts);
+	char buf[256];
+	struct priv_prog *skel;
+	int err;
+
+	skel = priv_prog__open_and_load();
+	if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) {
+		priv_prog__destroy(skel);
+		return -EINVAL;
+	}
+
+	/* use bpf_token_path to provide BPF FS path */
+	snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd);
+	opts.bpf_token_path = buf;
+	skel = priv_prog__open_opts(&opts);
+	if (!ASSERT_OK_PTR(skel, "obj_token_path_open"))
+		return -EINVAL;
+	err = priv_prog__load(skel);
+	priv_prog__destroy(skel);
+	if (!ASSERT_OK(err, "obj_token_path_load"))
+		return -EINVAL;
+
+	/* provide BPF token, but reject bpf_token_capable() with LSM */
+	lsm_skel->bss->reject_capable = true;
+	lsm_skel->bss->reject_cmd = false;
+	skel = priv_prog__open_opts(&opts);
+	if (!ASSERT_OK_PTR(skel, "obj_token_lsm_reject_cap_open"))
+		return -EINVAL;
+	err = priv_prog__load(skel);
+	priv_prog__destroy(skel);
+	if (!ASSERT_ERR(err, "obj_token_lsm_reject_cap_load"))
+		return -EINVAL;
+
+	/* provide BPF token, but reject bpf_token_cmd() with LSM */
+	lsm_skel->bss->reject_capable = false;
+	lsm_skel->bss->reject_cmd = true;
+	skel = priv_prog__open_opts(&opts);
+	if (!ASSERT_OK_PTR(skel, "obj_token_lsm_reject_cmd_open"))
+		return -EINVAL;
+	err = priv_prog__load(skel);
+	priv_prog__destroy(skel);
+	if (!ASSERT_ERR(err, "obj_token_lsm_reject_cmd_load"))
+		return -EINVAL;
+
+	return 0;
+}
+
+/* this test is called with BPF FS that doesn't delegate BPF_BTF_LOAD command,
+ * which should cause struct_ops application to fail, as BTF won't be uploaded
+ * into the kernel, even if STRUCT_OPS programs themselves are allowed
+ */
+static int validate_struct_ops_load(int mnt_fd, bool expect_success)
+{
+	LIBBPF_OPTS(bpf_object_open_opts, opts);
+	char buf[256];
+	struct dummy_st_ops_success *skel;
+	int err;
+
+	snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd);
+	opts.bpf_token_path = buf;
+	skel = dummy_st_ops_success__open_opts(&opts);
+	if (!ASSERT_OK_PTR(skel, "obj_token_path_open"))
+		return -EINVAL;
+
+	err = dummy_st_ops_success__load(skel);
+	dummy_st_ops_success__destroy(skel);
+	if (expect_success) {
+		if (!ASSERT_OK(err, "obj_token_path_load"))
+			return -EINVAL;
+	} else /* expect failure */ {
+		if (!ASSERT_ERR(err, "obj_token_path_load"))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int userns_obj_priv_btf_fail(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	return validate_struct_ops_load(mnt_fd, false /* should fail */);
+}
+
+static int userns_obj_priv_btf_success(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	return validate_struct_ops_load(mnt_fd, true /* should succeed */);
+}
+
+#define TOKEN_ENVVAR "LIBBPF_BPF_TOKEN_PATH"
+#define TOKEN_BPFFS_CUSTOM "/bpf-token-fs"
+
+static int userns_obj_priv_implicit_token(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	LIBBPF_OPTS(bpf_object_open_opts, opts);
+	struct dummy_st_ops_success *skel;
+	int err;
+
+	/* before we mount BPF FS with token delegation, struct_ops skeleton
+	 * should fail to load
+	 */
+	skel = dummy_st_ops_success__open_and_load();
+	if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) {
+		dummy_st_ops_success__destroy(skel);
+		return -EINVAL;
+	}
+
+	/* mount custom BPF FS over /sys/fs/bpf so that libbpf can create BPF
+	 * token automatically and implicitly
+	 */
+	err = sys_move_mount(mnt_fd, "", AT_FDCWD, "/sys/fs/bpf", MOVE_MOUNT_F_EMPTY_PATH);
+	if (!ASSERT_OK(err, "move_mount_bpffs"))
+		return -EINVAL;
+
+	/* disable implicit BPF token creation by setting
+	 * LIBBPF_BPF_TOKEN_PATH envvar to empty value, load should fail
+	 */
+	err = setenv(TOKEN_ENVVAR, "", 1 /*overwrite*/);
+	if (!ASSERT_OK(err, "setenv_token_path"))
+		return -EINVAL;
+	skel = dummy_st_ops_success__open_and_load();
+	if (!ASSERT_ERR_PTR(skel, "obj_token_envvar_disabled_load")) {
+		unsetenv(TOKEN_ENVVAR);
+		dummy_st_ops_success__destroy(skel);
+		return -EINVAL;
+	}
+	unsetenv(TOKEN_ENVVAR);
+
+	/* now the same struct_ops skeleton should succeed thanks to libppf
+	 * creating BPF token from /sys/fs/bpf mount point
+	 */
+	skel = dummy_st_ops_success__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "obj_implicit_token_load"))
+		return -EINVAL;
+
+	dummy_st_ops_success__destroy(skel);
+
+	/* now disable implicit token through empty bpf_token_path, should fail */
+	opts.bpf_token_path = "";
+	skel = dummy_st_ops_success__open_opts(&opts);
+	if (!ASSERT_OK_PTR(skel, "obj_empty_token_path_open"))
+		return -EINVAL;
+
+	err = dummy_st_ops_success__load(skel);
+	dummy_st_ops_success__destroy(skel);
+	if (!ASSERT_ERR(err, "obj_empty_token_path_load"))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int userns_obj_priv_implicit_token_envvar(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	LIBBPF_OPTS(bpf_object_open_opts, opts);
+	struct dummy_st_ops_success *skel;
+	int err;
+
+	/* before we mount BPF FS with token delegation, struct_ops skeleton
+	 * should fail to load
+	 */
+	skel = dummy_st_ops_success__open_and_load();
+	if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) {
+		dummy_st_ops_success__destroy(skel);
+		return -EINVAL;
+	}
+
+	/* mount custom BPF FS over custom location, so libbpf can't create
+	 * BPF token implicitly, unless pointed to it through
+	 * LIBBPF_BPF_TOKEN_PATH envvar
+	 */
+	rmdir(TOKEN_BPFFS_CUSTOM);
+	if (!ASSERT_OK(mkdir(TOKEN_BPFFS_CUSTOM, 0777), "mkdir_bpffs_custom"))
+		goto err_out;
+	err = sys_move_mount(mnt_fd, "", AT_FDCWD, TOKEN_BPFFS_CUSTOM, MOVE_MOUNT_F_EMPTY_PATH);
+	if (!ASSERT_OK(err, "move_mount_bpffs"))
+		goto err_out;
+
+	/* even though we have BPF FS with delegation, it's not at default
+	 * /sys/fs/bpf location, so we still fail to load until envvar is set up
+	 */
+	skel = dummy_st_ops_success__open_and_load();
+	if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load2")) {
+		dummy_st_ops_success__destroy(skel);
+		goto err_out;
+	}
+
+	err = setenv(TOKEN_ENVVAR, TOKEN_BPFFS_CUSTOM, 1 /*overwrite*/);
+	if (!ASSERT_OK(err, "setenv_token_path"))
+		goto err_out;
+
+	/* now the same struct_ops skeleton should succeed thanks to libppf
+	 * creating BPF token from custom mount point
+	 */
+	skel = dummy_st_ops_success__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "obj_implicit_token_load"))
+		goto err_out;
+
+	dummy_st_ops_success__destroy(skel);
+
+	/* now disable implicit token through empty bpf_token_path, envvar
+	 * will be ignored, should fail
+	 */
+	opts.bpf_token_path = "";
+	skel = dummy_st_ops_success__open_opts(&opts);
+	if (!ASSERT_OK_PTR(skel, "obj_empty_token_path_open"))
+		goto err_out;
+
+	err = dummy_st_ops_success__load(skel);
+	dummy_st_ops_success__destroy(skel);
+	if (!ASSERT_ERR(err, "obj_empty_token_path_load"))
+		goto err_out;
+
+	rmdir(TOKEN_BPFFS_CUSTOM);
+	unsetenv(TOKEN_ENVVAR);
+	return 0;
+err_out:
+	rmdir(TOKEN_BPFFS_CUSTOM);
+	unsetenv(TOKEN_ENVVAR);
+	return -EINVAL;
+}
+
+#define bit(n) (1ULL << (n))
+
+void test_token(void)
+{
+	if (test__start_subtest("map_token")) {
+		struct bpffs_opts opts = {
+			.cmds_str = "map_create",
+			.maps_str = "stack",
+		};
+
+		subtest_userns(&opts, userns_map_create);
+	}
+	if (test__start_subtest("btf_token")) {
+		struct bpffs_opts opts = {
+			.cmds = 1ULL << BPF_BTF_LOAD,
+		};
+
+		subtest_userns(&opts, userns_btf_load);
+	}
+	if (test__start_subtest("prog_token")) {
+		struct bpffs_opts opts = {
+			.cmds_str = "PROG_LOAD",
+			.progs_str = "XDP",
+			.attachs_str = "xdp",
+		};
+
+		subtest_userns(&opts, userns_prog_load);
+	}
+	if (test__start_subtest("obj_priv_map")) {
+		struct bpffs_opts opts = {
+			.cmds = bit(BPF_MAP_CREATE),
+			.maps = bit(BPF_MAP_TYPE_QUEUE),
+		};
+
+		subtest_userns(&opts, userns_obj_priv_map);
+	}
+	if (test__start_subtest("obj_priv_prog")) {
+		struct bpffs_opts opts = {
+			.cmds = bit(BPF_PROG_LOAD),
+			.progs = bit(BPF_PROG_TYPE_KPROBE),
+			.attachs = ~0ULL,
+		};
+
+		subtest_userns(&opts, userns_obj_priv_prog);
+	}
+	if (test__start_subtest("obj_priv_btf_fail")) {
+		struct bpffs_opts opts = {
+			/* disallow BTF loading */
+			.cmds = bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD),
+			.maps = bit(BPF_MAP_TYPE_STRUCT_OPS),
+			.progs = bit(BPF_PROG_TYPE_STRUCT_OPS),
+			.attachs = ~0ULL,
+		};
+
+		subtest_userns(&opts, userns_obj_priv_btf_fail);
+	}
+	if (test__start_subtest("obj_priv_btf_success")) {
+		struct bpffs_opts opts = {
+			/* allow BTF loading */
+			.cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD),
+			.maps = bit(BPF_MAP_TYPE_STRUCT_OPS),
+			.progs = bit(BPF_PROG_TYPE_STRUCT_OPS),
+			.attachs = ~0ULL,
+		};
+
+		subtest_userns(&opts, userns_obj_priv_btf_success);
+	}
+	if (test__start_subtest("obj_priv_implicit_token")) {
+		struct bpffs_opts opts = {
+			/* allow BTF loading */
+			.cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD),
+			.maps = bit(BPF_MAP_TYPE_STRUCT_OPS),
+			.progs = bit(BPF_PROG_TYPE_STRUCT_OPS),
+			.attachs = ~0ULL,
+		};
+
+		subtest_userns(&opts, userns_obj_priv_implicit_token);
+	}
+	if (test__start_subtest("obj_priv_implicit_token_envvar")) {
+		struct bpffs_opts opts = {
+			/* allow BTF loading */
+			.cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD),
+			.maps = bit(BPF_MAP_TYPE_STRUCT_OPS),
+			.progs = bit(BPF_PROG_TYPE_STRUCT_OPS),
+			.attachs = ~0ULL,
+		};
+
+		subtest_userns(&opts, userns_obj_priv_implicit_token_envvar);
+	}
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tracing_failure.c b/tools/testing/selftests/bpf/prog_tests/tracing_failure.c
new file mode 100644
index 0000000000..a222df765b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tracing_failure.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include "tracing_failure.skel.h"
+
+static void test_bpf_spin_lock(bool is_spin_lock)
+{
+	struct tracing_failure *skel;
+	int err;
+
+	skel = tracing_failure__open();
+	if (!ASSERT_OK_PTR(skel, "tracing_failure__open"))
+		return;
+
+	if (is_spin_lock)
+		bpf_program__set_autoload(skel->progs.test_spin_lock, true);
+	else
+		bpf_program__set_autoload(skel->progs.test_spin_unlock, true);
+
+	err = tracing_failure__load(skel);
+	if (!ASSERT_OK(err, "tracing_failure__load"))
+		goto out;
+
+	err = tracing_failure__attach(skel);
+	ASSERT_ERR(err, "tracing_failure__attach");
+
+out:
+	tracing_failure__destroy(skel);
+}
+
+void test_tracing_failure(void)
+{
+	if (test__start_subtest("bpf_spin_lock"))
+		test_bpf_spin_lock(true);
+	if (test__start_subtest("bpf_spin_unlock"))
+		test_bpf_spin_lock(false);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index d62c5bf00e..c4f9f30664 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -4,6 +4,8 @@
 
 #include "cap_helpers.h"
 #include "verifier_and.skel.h"
+#include "verifier_arena.skel.h"
+#include "verifier_arena_large.skel.h"
 #include "verifier_array_access.skel.h"
 #include "verifier_basic_stack.skel.h"
 #include "verifier_bitfield_write.skel.h"
@@ -28,6 +30,7 @@
 #include "verifier_div0.skel.h"
 #include "verifier_div_overflow.skel.h"
 #include "verifier_global_subprogs.skel.h"
+#include "verifier_global_ptr_args.skel.h"
 #include "verifier_gotol.skel.h"
 #include "verifier_helper_access_var_len.skel.h"
 #include "verifier_helper_packet_access.skel.h"
@@ -117,6 +120,8 @@ static void run_tests_aux(const char *skel_name,
 #define RUN(skel) run_tests_aux(#skel, skel##__elf_bytes, NULL)
 
 void test_verifier_and(void)                  { RUN(verifier_and); }
+void test_verifier_arena(void)                { RUN(verifier_arena); }
+void test_verifier_arena_large(void)          { RUN(verifier_arena_large); }
 void test_verifier_basic_stack(void)          { RUN(verifier_basic_stack); }
 void test_verifier_bitfield_write(void)       { RUN(verifier_bitfield_write); }
 void test_verifier_bounds(void)               { RUN(verifier_bounds); }
@@ -140,6 +145,7 @@ void test_verifier_direct_stack_access_wraparound(void) { RUN(verifier_direct_st
 void test_verifier_div0(void)                 { RUN(verifier_div0); }
 void test_verifier_div_overflow(void)         { RUN(verifier_div_overflow); }
 void test_verifier_global_subprogs(void)      { RUN(verifier_global_subprogs); }
+void test_verifier_global_ptr_args(void)      { RUN(verifier_global_ptr_args); }
 void test_verifier_gotol(void)                { RUN(verifier_gotol); }
 void test_verifier_helper_access_var_len(void) { RUN(verifier_helper_access_var_len); }
 void test_verifier_helper_packet_access(void) { RUN(verifier_helper_packet_access); }
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
index bad0ea167b..498d3bdaa4 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
@@ -107,8 +107,8 @@ void test_xdp_do_redirect(void)
 			    .attach_point = BPF_TC_INGRESS);
 
 	memcpy(&data[sizeof(__u64)], &pkt_udp, sizeof(pkt_udp));
-	((__u32 *)data)[0] = 0x42; /* metadata test value */
-	((__u32 *)data)[1] = 0;
+	*((__u32 *)data) = 0x42; /* metadata test value */
+	*((__u32 *)data + 4) = 0;
 
 	skel = test_xdp_do_redirect__open();
 	if (!ASSERT_OK_PTR(skel, "skel"))
diff --git a/tools/testing/selftests/bpf/prog_tests/xdpwall.c b/tools/testing/selftests/bpf/prog_tests/xdpwall.c
index f3927829a5..4599154c8e 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdpwall.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdpwall.c
@@ -9,7 +9,7 @@ void test_xdpwall(void)
 	struct xdpwall *skel;
 
 	skel = xdpwall__open_and_load();
-	ASSERT_OK_PTR(skel, "Does LLMV have https://reviews.llvm.org/D109073?");
+	ASSERT_OK_PTR(skel, "Does LLVM have https://github.com/llvm/llvm-project/commit/ea72b0319d7b0f0c2fcf41d121afa5d031b319d5?");
 
 	xdpwall__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/progs/arena_htab.c b/tools/testing/selftests/bpf/progs/arena_htab.c
new file mode 100644
index 0000000000..1e6ac187a6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/arena_htab.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_experimental.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, 100); /* number of pages */
+} arena SEC(".maps");
+
+#include "bpf_arena_htab.h"
+
+void __arena *htab_for_user;
+bool skip = false;
+
+int zero = 0;
+
+SEC("syscall")
+int arena_htab_llvm(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST) || defined(BPF_ARENA_FORCE_ASM)
+	struct htab __arena *htab;
+	__u64 i;
+
+	htab = bpf_alloc(sizeof(*htab));
+	cast_kern(htab);
+	htab_init(htab);
+
+	/* first run. No old elems in the table */
+	for (i = zero; i < 1000; i++)
+		htab_update_elem(htab, i, i);
+
+	/* should replace all elems with new ones */
+	for (i = zero; i < 1000; i++)
+		htab_update_elem(htab, i, i);
+	cast_user(htab);
+	htab_for_user = htab;
+#else
+	skip = true;
+#endif
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/arena_htab_asm.c b/tools/testing/selftests/bpf/progs/arena_htab_asm.c
new file mode 100644
index 0000000000..6cd70ea12f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/arena_htab_asm.c
@@ -0,0 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#define BPF_ARENA_FORCE_ASM
+#define arena_htab_llvm arena_htab_asm
+#include "arena_htab.c"
diff --git a/tools/testing/selftests/bpf/progs/arena_list.c b/tools/testing/selftests/bpf/progs/arena_list.c
new file mode 100644
index 0000000000..c0422c58ce
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/arena_list.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_experimental.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");
+
+#include "bpf_arena_alloc.h"
+#include "bpf_arena_list.h"
+
+struct elem {
+	struct arena_list_node node;
+	__u64 value;
+};
+
+struct arena_list_head __arena *list_head;
+int list_sum;
+int cnt;
+bool skip = false;
+
+#ifdef __BPF_FEATURE_ADDR_SPACE_CAST
+long __arena arena_sum;
+int __arena test_val = 1;
+struct arena_list_head __arena global_head;
+#else
+long arena_sum SEC(".addr_space.1");
+int test_val SEC(".addr_space.1");
+#endif
+
+int zero;
+
+SEC("syscall")
+int arena_list_add(void *ctx)
+{
+#ifdef __BPF_FEATURE_ADDR_SPACE_CAST
+	__u64 i;
+
+	list_head = &global_head;
+
+	for (i = zero; i < cnt; cond_break, i++) {
+		struct elem __arena *n = bpf_alloc(sizeof(*n));
+
+		test_val++;
+		n->value = i;
+		arena_sum += i;
+		list_add_head(&n->node, list_head);
+	}
+#else
+	skip = true;
+#endif
+	return 0;
+}
+
+SEC("syscall")
+int arena_list_del(void *ctx)
+{
+#ifdef __BPF_FEATURE_ADDR_SPACE_CAST
+	struct elem __arena *n;
+	int sum = 0;
+
+	arena_sum = 0;
+	list_for_each_entry(n, list_head, node) {
+		sum += n->value;
+		arena_sum += n->value;
+		list_del(&n->node);
+		bpf_free(n);
+	}
+	list_sum = sum;
+#else
+	skip = true;
+#endif
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/async_stack_depth.c b/tools/testing/selftests/bpf/progs/async_stack_depth.c
index 3517c0e012..36734683ac 100644
--- a/tools/testing/selftests/bpf/progs/async_stack_depth.c
+++ b/tools/testing/selftests/bpf/progs/async_stack_depth.c
@@ -30,7 +30,7 @@ static int bad_timer_cb(void *map, int *key, struct bpf_timer *timer)
 }
 
 SEC("tc")
-__failure __msg("combined stack size of 2 calls is 576. Too large")
+__failure __msg("combined stack size of 2 calls is")
 int pseudo_call_check(struct __sk_buff *ctx)
 {
 	struct hmap_elem *elem;
@@ -45,7 +45,7 @@ int pseudo_call_check(struct __sk_buff *ctx)
 }
 
 SEC("tc")
-__failure __msg("combined stack size of 2 calls is 608. Too large")
+__failure __msg("combined stack size of 2 calls is")
 int async_call_root_check(struct __sk_buff *ctx)
 {
 	struct hmap_elem *elem;
diff --git a/tools/testing/selftests/bpf/progs/bad_struct_ops.c b/tools/testing/selftests/bpf/progs/bad_struct_ops.c
new file mode 100644
index 0000000000..b7e175cd0a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bad_struct_ops.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../bpf_testmod/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("struct_ops/test_1")
+int BPF_PROG(test_1) { return 0; }
+
+SEC("struct_ops/test_2")
+int BPF_PROG(test_2) { return 0; }
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_1 = {
+	.test_1 = (void *)test_1,
+	.test_2 = (void *)test_2
+};
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops2 testmod_2 = {
+	.test_1 = (void *)test_1
+};
diff --git a/tools/testing/selftests/bpf/progs/bad_struct_ops2.c b/tools/testing/selftests/bpf/progs/bad_struct_ops2.c
new file mode 100644
index 0000000000..64a95f6be8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bad_struct_ops2.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+/* This is an unused struct_ops program, it lacks corresponding
+ * struct_ops map, which provides attachment information.
+ * W/o additional configuration attempt to load such
+ * BPF object file would fail.
+ */
+SEC("struct_ops/foo")
+void foo(void) {}
diff --git a/tools/testing/selftests/bpf/progs/bench_local_storage_create.c b/tools/testing/selftests/bpf/progs/bench_local_storage_create.c
index c8ec0d0368..e4bfbba6c1 100644
--- a/tools/testing/selftests/bpf/progs/bench_local_storage_create.c
+++ b/tools/testing/selftests/bpf/progs/bench_local_storage_create.c
@@ -61,15 +61,14 @@ SEC("lsm.s/socket_post_create")
 int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
 	     int protocol, int kern)
 {
-	struct sock *sk = sock->sk;
 	struct storage *stg;
 	__u32 pid;
 
 	pid = bpf_get_current_pid_tgid() >> 32;
-	if (pid != bench_pid || !sk)
+	if (pid != bench_pid)
 		return 0;
 
-	stg = bpf_sk_storage_get(&sk_storage_map, sk, NULL,
+	stg = bpf_sk_storage_get(&sk_storage_map, sock->sk, NULL,
 				 BPF_LOCAL_STORAGE_GET_F_CREATE);
 
 	if (stg)
diff --git a/tools/testing/selftests/bpf/progs/bpf_compiler.h b/tools/testing/selftests/bpf/progs/bpf_compiler.h
new file mode 100644
index 0000000000..a7c343dc82
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_compiler.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BPF_COMPILER_H__
+#define __BPF_COMPILER_H__
+
+#define DO_PRAGMA_(X) _Pragma(#X)
+
+#if __clang__
+#define __pragma_loop_unroll DO_PRAGMA_(clang loop unroll(enable))
+#else
+/* In GCC -funroll-loops, which is enabled with -O2, should have the
+   same impact than the loop-unroll-enable pragma above.  */
+#define __pragma_loop_unroll
+#endif
+
+#if __clang__
+#define __pragma_loop_unroll_count(N) DO_PRAGMA_(clang loop unroll_count(N))
+#else
+#define __pragma_loop_unroll_count(N) DO_PRAGMA_(GCC unroll N)
+#endif
+
+#if __clang__
+#define __pragma_loop_unroll_full DO_PRAGMA_(clang loop unroll(full))
+#else
+#define __pragma_loop_unroll_full DO_PRAGMA_(GCC unroll 65534)
+#endif
+
+#if __clang__
+#define __pragma_loop_no_unroll DO_PRAGMA_(clang loop unroll(disable))
+#else
+#define __pragma_loop_no_unroll DO_PRAGMA_(GCC unroll 1)
+#endif
+
+#endif
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index 2fd59970c4..fb2f5513e2 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -80,7 +80,7 @@
 #define __imm(name) [name]"i"(name)
 #define __imm_const(name, expr) [name]"i"(expr)
 #define __imm_addr(name) [name]"i"(&name)
-#define __imm_ptr(name) [name]"p"(&name)
+#define __imm_ptr(name) [name]"r"(&name)
 #define __imm_insn(name, expr) [name]"i"(*(long *)&(expr))
 
 /* Magic constants used with __retval() */
diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
index e8bd4b7b5e..7001965d1c 100644
--- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
+++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
@@ -51,9 +51,25 @@
 #define ICSK_TIME_LOSS_PROBE	5
 #define ICSK_TIME_REO_TIMEOUT	6
 
+#define ETH_ALEN		6
 #define ETH_HLEN		14
+#define ETH_P_IP		0x0800
 #define ETH_P_IPV6		0x86DD
 
+#define NEXTHDR_TCP		6
+
+#define TCPOPT_NOP		1
+#define TCPOPT_EOL		0
+#define TCPOPT_MSS		2
+#define TCPOPT_WINDOW		3
+#define TCPOPT_TIMESTAMP	8
+#define TCPOPT_SACK_PERM	4
+
+#define TCPOLEN_MSS		4
+#define TCPOLEN_WINDOW		3
+#define TCPOLEN_TIMESTAMP	10
+#define TCPOLEN_SACK_PERM	2
+
 #define CHECKSUM_NONE		0
 #define CHECKSUM_PARTIAL	3
 
diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c b/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c
index 610c2427fd..3500e4b69e 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c
@@ -27,32 +27,6 @@ bool is_cgroup1 = 0;
 struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym;
 void bpf_cgroup_release(struct cgroup *cgrp) __ksym;
 
-static void __on_lookup(struct cgroup *cgrp)
-{
-	bpf_cgrp_storage_delete(&map_a, cgrp);
-	bpf_cgrp_storage_delete(&map_b, cgrp);
-}
-
-SEC("fentry/bpf_local_storage_lookup")
-int BPF_PROG(on_lookup)
-{
-	struct task_struct *task = bpf_get_current_task_btf();
-	struct cgroup *cgrp;
-
-	if (is_cgroup1) {
-		cgrp = bpf_task_get_cgroup1(task, target_hid);
-		if (!cgrp)
-			return 0;
-
-		__on_lookup(cgrp);
-		bpf_cgroup_release(cgrp);
-		return 0;
-	}
-
-	__on_lookup(task->cgroups->dfl_cgrp);
-	return 0;
-}
-
 static void __on_update(struct cgroup *cgrp)
 {
 	long *ptr;
diff --git a/tools/testing/selftests/bpf/progs/connect_unix_prog.c b/tools/testing/selftests/bpf/progs/connect_unix_prog.c
index ca8aa2f116..2ef0e0c46d 100644
--- a/tools/testing/selftests/bpf/progs/connect_unix_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect_unix_prog.c
@@ -28,8 +28,7 @@ int connect_unix_prog(struct bpf_sock_addr *ctx)
 	if (sa_kern->uaddrlen != unaddrlen)
 		return 0;
 
-	sa_kern_unaddr = bpf_rdonly_cast(sa_kern->uaddr,
-						bpf_core_type_id_kernel(struct sockaddr_un));
+	sa_kern_unaddr = bpf_core_cast(sa_kern->uaddr, struct sockaddr_un);
 	if (memcmp(sa_kern_unaddr->sun_path, SERVUN_REWRITE_ADDRESS,
 			sizeof(SERVUN_REWRITE_ADDRESS) - 1) != 0)
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/cpumask_common.h b/tools/testing/selftests/bpf/progs/cpumask_common.h
index 0cd4aebb97..c705d8112a 100644
--- a/tools/testing/selftests/bpf/progs/cpumask_common.h
+++ b/tools/testing/selftests/bpf/progs/cpumask_common.h
@@ -23,41 +23,42 @@ struct array_map {
 	__uint(max_entries, 1);
 } __cpumask_map SEC(".maps");
 
-struct bpf_cpumask *bpf_cpumask_create(void) __ksym;
-void bpf_cpumask_release(struct bpf_cpumask *cpumask) __ksym;
-struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) __ksym;
-u32 bpf_cpumask_first(const struct cpumask *cpumask) __ksym;
-u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) __ksym;
+struct bpf_cpumask *bpf_cpumask_create(void) __ksym __weak;
+void bpf_cpumask_release(struct bpf_cpumask *cpumask) __ksym __weak;
+struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) __ksym __weak;
+u32 bpf_cpumask_first(const struct cpumask *cpumask) __ksym __weak;
+u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) __ksym __weak;
 u32 bpf_cpumask_first_and(const struct cpumask *src1,
-			  const struct cpumask *src2) __ksym;
-void bpf_cpumask_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym;
-void bpf_cpumask_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym;
-bool bpf_cpumask_test_cpu(u32 cpu, const struct cpumask *cpumask) __ksym;
-bool bpf_cpumask_test_and_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym;
-bool bpf_cpumask_test_and_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym;
-void bpf_cpumask_setall(struct bpf_cpumask *cpumask) __ksym;
-void bpf_cpumask_clear(struct bpf_cpumask *cpumask) __ksym;
+			  const struct cpumask *src2) __ksym __weak;
+void bpf_cpumask_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym __weak;
+void bpf_cpumask_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym __weak;
+bool bpf_cpumask_test_cpu(u32 cpu, const struct cpumask *cpumask) __ksym __weak;
+bool bpf_cpumask_test_and_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym __weak;
+bool bpf_cpumask_test_and_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym __weak;
+void bpf_cpumask_setall(struct bpf_cpumask *cpumask) __ksym __weak;
+void bpf_cpumask_clear(struct bpf_cpumask *cpumask) __ksym __weak;
 bool bpf_cpumask_and(struct bpf_cpumask *cpumask,
 		     const struct cpumask *src1,
-		     const struct cpumask *src2) __ksym;
+		     const struct cpumask *src2) __ksym __weak;
 void bpf_cpumask_or(struct bpf_cpumask *cpumask,
 		    const struct cpumask *src1,
-		    const struct cpumask *src2) __ksym;
+		    const struct cpumask *src2) __ksym __weak;
 void bpf_cpumask_xor(struct bpf_cpumask *cpumask,
 		     const struct cpumask *src1,
-		     const struct cpumask *src2) __ksym;
-bool bpf_cpumask_equal(const struct cpumask *src1, const struct cpumask *src2) __ksym;
-bool bpf_cpumask_intersects(const struct cpumask *src1, const struct cpumask *src2) __ksym;
-bool bpf_cpumask_subset(const struct cpumask *src1, const struct cpumask *src2) __ksym;
-bool bpf_cpumask_empty(const struct cpumask *cpumask) __ksym;
-bool bpf_cpumask_full(const struct cpumask *cpumask) __ksym;
-void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) __ksym;
-u32 bpf_cpumask_any_distribute(const struct cpumask *src) __ksym;
-u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1, const struct cpumask *src2) __ksym;
-u32 bpf_cpumask_weight(const struct cpumask *cpumask) __ksym;
-
-void bpf_rcu_read_lock(void) __ksym;
-void bpf_rcu_read_unlock(void) __ksym;
+		     const struct cpumask *src2) __ksym __weak;
+bool bpf_cpumask_equal(const struct cpumask *src1, const struct cpumask *src2) __ksym __weak;
+bool bpf_cpumask_intersects(const struct cpumask *src1, const struct cpumask *src2) __ksym __weak;
+bool bpf_cpumask_subset(const struct cpumask *src1, const struct cpumask *src2) __ksym __weak;
+bool bpf_cpumask_empty(const struct cpumask *cpumask) __ksym __weak;
+bool bpf_cpumask_full(const struct cpumask *cpumask) __ksym __weak;
+void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) __ksym __weak;
+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;
+
+void bpf_rcu_read_lock(void) __ksym __weak;
+void bpf_rcu_read_unlock(void) __ksym __weak;
 
 static inline const struct cpumask *cast(struct bpf_cpumask *cpumask)
 {
diff --git a/tools/testing/selftests/bpf/progs/getpeername_unix_prog.c b/tools/testing/selftests/bpf/progs/getpeername_unix_prog.c
index 9c078f34bb..5a76754f84 100644
--- a/tools/testing/selftests/bpf/progs/getpeername_unix_prog.c
+++ b/tools/testing/selftests/bpf/progs/getpeername_unix_prog.c
@@ -27,8 +27,7 @@ int getpeername_unix_prog(struct bpf_sock_addr *ctx)
 	if (sa_kern->uaddrlen != unaddrlen)
 		return 1;
 
-	sa_kern_unaddr = bpf_rdonly_cast(sa_kern->uaddr,
-						bpf_core_type_id_kernel(struct sockaddr_un));
+	sa_kern_unaddr = bpf_core_cast(sa_kern->uaddr, struct sockaddr_un);
 	if (memcmp(sa_kern_unaddr->sun_path, SERVUN_REWRITE_ADDRESS,
 			sizeof(SERVUN_REWRITE_ADDRESS) - 1) != 0)
 		return 1;
diff --git a/tools/testing/selftests/bpf/progs/getsockname_unix_prog.c b/tools/testing/selftests/bpf/progs/getsockname_unix_prog.c
index ac71451114..7867113c69 100644
--- a/tools/testing/selftests/bpf/progs/getsockname_unix_prog.c
+++ b/tools/testing/selftests/bpf/progs/getsockname_unix_prog.c
@@ -27,8 +27,7 @@ int getsockname_unix_prog(struct bpf_sock_addr *ctx)
 	if (sa_kern->uaddrlen != unaddrlen)
 		return 1;
 
-	sa_kern_unaddr = bpf_rdonly_cast(sa_kern->uaddr,
-						bpf_core_type_id_kernel(struct sockaddr_un));
+	sa_kern_unaddr = bpf_core_cast(sa_kern->uaddr, struct sockaddr_un);
 	if (memcmp(sa_kern_unaddr->sun_path, SERVUN_REWRITE_ADDRESS,
 			sizeof(SERVUN_REWRITE_ADDRESS) - 1) != 0)
 		return 1;
diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
index fe971992e6..3db416606f 100644
--- a/tools/testing/selftests/bpf/progs/iters.c
+++ b/tools/testing/selftests/bpf/progs/iters.c
@@ -5,6 +5,7 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
+#include "bpf_compiler.h"
 
 #define ARRAY_SIZE(x) (int)(sizeof(x) / sizeof((x)[0]))
 
@@ -78,8 +79,8 @@ int iter_err_unsafe_asm_loop(const void *ctx)
 		"*(u32 *)(r1 + 0) = r6;" /* invalid */
 		:
 		: [it]"r"(&it),
-		  [small_arr]"p"(small_arr),
-		  [zero]"p"(zero),
+		  [small_arr]"r"(small_arr),
+		  [zero]"r"(zero),
 		  __imm(bpf_iter_num_new),
 		  __imm(bpf_iter_num_next),
 		  __imm(bpf_iter_num_destroy)
@@ -183,7 +184,7 @@ int iter_pragma_unroll_loop(const void *ctx)
 	MY_PID_GUARD();
 
 	bpf_iter_num_new(&it, 0, 2);
-#pragma nounroll
+	__pragma_loop_no_unroll
 	for (i = 0; i < 3; i++) {
 		v = bpf_iter_num_next(&it);
 		bpf_printk("ITER_BASIC: E3 VAL: i=%d v=%d", i, v ? *v : -1);
@@ -238,7 +239,7 @@ int iter_multiple_sequential_loops(const void *ctx)
 	bpf_iter_num_destroy(&it);
 
 	bpf_iter_num_new(&it, 0, 2);
-#pragma nounroll
+	__pragma_loop_no_unroll
 	for (i = 0; i < 3; i++) {
 		v = bpf_iter_num_next(&it);
 		bpf_printk("ITER_BASIC: E3 VAL: i=%d v=%d", i, v ? *v : -1);
diff --git a/tools/testing/selftests/bpf/progs/kptr_xchg_inline.c b/tools/testing/selftests/bpf/progs/kptr_xchg_inline.c
new file mode 100644
index 0000000000..2414ac20b6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kptr_xchg_inline.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_experimental.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct bin_data {
+	char blob[32];
+};
+
+#define private(name) SEC(".bss." #name) __hidden __attribute__((aligned(8)))
+private(kptr) struct bin_data __kptr * ptr;
+
+SEC("tc")
+__naked int kptr_xchg_inline(void)
+{
+	asm volatile (
+		"r1 = %[ptr] ll;"
+		"r2 = 0;"
+		"call %[bpf_kptr_xchg];"
+		"if r0 == 0 goto 1f;"
+		"r1 = r0;"
+		"r2 = 0;"
+		"call %[bpf_obj_drop_impl];"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm_addr(ptr),
+		  __imm(bpf_kptr_xchg),
+		  __imm(bpf_obj_drop_impl)
+		: __clobber_all
+	);
+}
+
+/* BTF FUNC records are not generated for kfuncs referenced
+ * from inline assembly. These records are necessary for
+ * libbpf to link the program. The function below is a hack
+ * to ensure that BTF FUNC records are generated.
+ */
+void __btf_root(void)
+{
+	bpf_obj_drop(NULL);
+}
diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c
index 637e75df2e..e5e3a8b8dd 100644
--- a/tools/testing/selftests/bpf/progs/local_storage.c
+++ b/tools/testing/selftests/bpf/progs/local_storage.c
@@ -140,12 +140,11 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address,
 {
 	__u32 pid = bpf_get_current_pid_tgid() >> 32;
 	struct local_storage *storage;
-	struct sock *sk = sock->sk;
 
-	if (pid != monitored_pid || !sk)
+	if (pid != monitored_pid)
 		return 0;
 
-	storage = bpf_sk_storage_get(&sk_storage_map, sk, 0, 0);
+	storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0, 0);
 	if (!storage)
 		return 0;
 
@@ -156,24 +155,24 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address,
 	/* This tests that we can associate multiple elements
 	 * with the local storage.
 	 */
-	storage = bpf_sk_storage_get(&sk_storage_map2, sk, 0,
+	storage = bpf_sk_storage_get(&sk_storage_map2, sock->sk, 0,
 				     BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!storage)
 		return 0;
 
-	if (bpf_sk_storage_delete(&sk_storage_map2, sk))
+	if (bpf_sk_storage_delete(&sk_storage_map2, sock->sk))
 		return 0;
 
-	storage = bpf_sk_storage_get(&sk_storage_map2, sk, 0,
+	storage = bpf_sk_storage_get(&sk_storage_map2, sock->sk, 0,
 				     BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!storage)
 		return 0;
 
-	if (bpf_sk_storage_delete(&sk_storage_map, sk))
+	if (bpf_sk_storage_delete(&sk_storage_map, sock->sk))
 		return 0;
 
 	/* Ensure that the sk_storage_map is disconnected from the storage. */
-	if (!sk->sk_bpf_storage || sk->sk_bpf_storage->smap)
+	if (!sock->sk->sk_bpf_storage || sock->sk->sk_bpf_storage->smap)
 		return 0;
 
 	sk_storage_result = 0;
@@ -186,12 +185,11 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
 {
 	__u32 pid = bpf_get_current_pid_tgid() >> 32;
 	struct local_storage *storage;
-	struct sock *sk = sock->sk;
 
-	if (pid != monitored_pid || !sk)
+	if (pid != monitored_pid)
 		return 0;
 
-	storage = bpf_sk_storage_get(&sk_storage_map, sk, 0,
+	storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0,
 				     BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!storage)
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/loop4.c b/tools/testing/selftests/bpf/progs/loop4.c
index b35337926d..0de0357f57 100644
--- a/tools/testing/selftests/bpf/progs/loop4.c
+++ b/tools/testing/selftests/bpf/progs/loop4.c
@@ -3,6 +3,8 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
+#include "bpf_compiler.h"
+
 char _license[] SEC("license") = "GPL";
 
 SEC("socket")
@@ -10,7 +12,7 @@ int combinations(volatile struct __sk_buff* skb)
 {
 	int ret = 0, i;
 
-#pragma nounroll
+	__pragma_loop_no_unroll
 	for (i = 0; i < 20; i++)
 		if (skb->len)
 			ret |= 1 << i;
diff --git a/tools/testing/selftests/bpf/progs/lsm_cgroup.c b/tools/testing/selftests/bpf/progs/lsm_cgroup.c
index d7598538aa..02c11d16b6 100644
--- a/tools/testing/selftests/bpf/progs/lsm_cgroup.c
+++ b/tools/testing/selftests/bpf/progs/lsm_cgroup.c
@@ -103,15 +103,11 @@ static __always_inline int real_bind(struct socket *sock,
 				     int addrlen)
 {
 	struct sockaddr_ll sa = {};
-	struct sock *sk = sock->sk;
 
-	if (!sk)
-		return 1;
-
-	if (sk->__sk_common.skc_family != AF_PACKET)
+	if (sock->sk->__sk_common.skc_family != AF_PACKET)
 		return 1;
 
-	if (sk->sk_kern_sock)
+	if (sock->sk->sk_kern_sock)
 		return 1;
 
 	bpf_probe_read_kernel(&sa, sizeof(sa), address);
diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
index 3325da17ec..efaf622c28 100644
--- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c
+++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
@@ -316,7 +316,7 @@ struct lpm_trie {
 } __attribute__((preserve_access_index));
 
 struct lpm_key {
-	struct bpf_lpm_trie_key trie_key;
+	struct bpf_lpm_trie_key_hdr trie_key;
 	__u32 data;
 };
 
diff --git a/tools/testing/selftests/bpf/progs/priv_map.c b/tools/testing/selftests/bpf/progs/priv_map.c
new file mode 100644
index 0000000000..9085be50f0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/priv_map.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_QUEUE);
+	__uint(max_entries, 1);
+	__type(value, __u32);
+} priv_map SEC(".maps");
diff --git a/tools/testing/selftests/bpf/progs/priv_prog.c b/tools/testing/selftests/bpf/progs/priv_prog.c
new file mode 100644
index 0000000000..3c7b2b618c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/priv_prog.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC("kprobe")
+int kprobe_prog(void *ctx)
+{
+	return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h
index de3b6e4e4d..6957d9f280 100644
--- a/tools/testing/selftests/bpf/progs/profiler.inc.h
+++ b/tools/testing/selftests/bpf/progs/profiler.inc.h
@@ -8,6 +8,7 @@
 #include "profiler.h"
 #include "err.h"
 #include "bpf_experimental.h"
+#include "bpf_compiler.h"
 
 #ifndef NULL
 #define NULL 0
@@ -169,7 +170,7 @@ static INLINE int get_var_spid_index(struct var_kill_data_arr_t* arr_struct,
 				     int spid)
 {
 #ifdef UNROLL
-#pragma unroll
+	__pragma_loop_unroll
 #endif
 	for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++)
 		if (arr_struct->array[i].meta.pid == spid)
@@ -185,7 +186,7 @@ static INLINE void populate_ancestors(struct task_struct* task,
 
 	ancestors_data->num_ancestors = 0;
 #ifdef UNROLL
-#pragma unroll
+	__pragma_loop_unroll
 #endif
 	for (num_ancestors = 0; num_ancestors < MAX_ANCESTORS; num_ancestors++) {
 		parent = BPF_CORE_READ(parent, real_parent);
@@ -212,7 +213,7 @@ static INLINE void* read_full_cgroup_path(struct kernfs_node* cgroup_node,
 	size_t filepart_length;
 
 #ifdef UNROLL
-#pragma unroll
+	__pragma_loop_unroll
 #endif
 	for (int i = 0; i < MAX_CGROUPS_PATH_DEPTH; i++) {
 		filepart_length =
@@ -261,7 +262,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data,
 		int cgrp_id = bpf_core_enum_value(enum cgroup_subsys_id___local,
 						  pids_cgrp_id___local);
 #ifdef UNROLL
-#pragma unroll
+		__pragma_loop_unroll
 #endif
 		for (int i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
 			struct cgroup_subsys_state* subsys =
@@ -402,7 +403,7 @@ static INLINE int trace_var_sys_kill(void* ctx, int tpid, int sig)
 			if (kill_data == NULL)
 				return 0;
 #ifdef UNROLL
-#pragma unroll
+			__pragma_loop_unroll
 #endif
 			for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++)
 				if (arr_struct->array[i].meta.pid == 0) {
@@ -482,7 +483,7 @@ read_absolute_file_path_from_dentry(struct dentry* filp_dentry, void* payload)
 	struct dentry* parent_dentry;
 
 #ifdef UNROLL
-#pragma unroll
+	__pragma_loop_unroll
 #endif
 	for (int i = 0; i < MAX_PATH_DEPTH; i++) {
 		filepart_length =
@@ -508,7 +509,7 @@ is_ancestor_in_allowed_inodes(struct dentry* filp_dentry)
 {
 	struct dentry* parent_dentry;
 #ifdef UNROLL
-#pragma unroll
+	__pragma_loop_unroll
 #endif
 	for (int i = 0; i < MAX_PATH_DEPTH; i++) {
 		u64 dir_ino = BPF_CORE_READ(filp_dentry, d_inode, i_ino);
@@ -629,7 +630,7 @@ int raw_tracepoint__sched_process_exit(void* ctx)
 	struct kernfs_node* proc_kernfs = BPF_CORE_READ(task, cgroups, dfl_cgrp, kn);
 
 #ifdef UNROLL
-#pragma unroll
+	__pragma_loop_unroll
 #endif
 	for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++) {
 		struct var_kill_data_t* past_kill_data = &arr_struct->array[i];
diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h
index 026d573ce1..86484f07e1 100644
--- a/tools/testing/selftests/bpf/progs/pyperf.h
+++ b/tools/testing/selftests/bpf/progs/pyperf.h
@@ -8,6 +8,7 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
+#include "bpf_compiler.h"
 
 #define FUNCTION_NAME_LEN 64
 #define FILE_NAME_LEN 128
@@ -298,11 +299,11 @@ int __on_event(struct bpf_raw_tracepoint_args *ctx)
 #if defined(USE_ITER)
 /* no for loop, no unrolling */
 #elif defined(NO_UNROLL)
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 #elif defined(UNROLL_COUNT)
-#pragma clang loop unroll_count(UNROLL_COUNT)
+	__pragma_loop_unroll_count(UNROLL_COUNT)
 #else
-#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 #endif /* NO_UNROLL */
 		/* Unwind python stack */
 #ifdef USE_ITER
diff --git a/tools/testing/selftests/bpf/progs/rcu_read_lock.c b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
index 14fb01437f..ab3a532b7d 100644
--- a/tools/testing/selftests/bpf/progs/rcu_read_lock.c
+++ b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
@@ -319,3 +319,123 @@ int cross_rcu_region(void *ctx)
 	bpf_rcu_read_unlock();
 	return 0;
 }
+
+__noinline
+static int static_subprog(void *ctx)
+{
+	volatile int ret = 0;
+
+	if (bpf_get_prandom_u32())
+		return ret + 42;
+	return ret + bpf_get_prandom_u32();
+}
+
+__noinline
+int global_subprog(u64 a)
+{
+	volatile int ret = a;
+
+	return ret + static_subprog(NULL);
+}
+
+__noinline
+static int static_subprog_lock(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	if (bpf_get_prandom_u32())
+		return ret + 42;
+	return ret + bpf_get_prandom_u32();
+}
+
+__noinline
+int global_subprog_lock(u64 a)
+{
+	volatile int ret = a;
+
+	return ret + static_subprog_lock(NULL);
+}
+
+__noinline
+static int static_subprog_unlock(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_unlock();
+	if (bpf_get_prandom_u32())
+		return ret + 42;
+	return ret + bpf_get_prandom_u32();
+}
+
+__noinline
+int global_subprog_unlock(u64 a)
+{
+	volatile int ret = a;
+
+	return ret + static_subprog_unlock(NULL);
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_subprog(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	if (bpf_get_prandom_u32())
+		ret += static_subprog(ctx);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_global_subprog(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	if (bpf_get_prandom_u32())
+		ret += global_subprog(ret);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_subprog_lock(void *ctx)
+{
+	volatile int ret = 0;
+
+	ret += static_subprog_lock(ctx);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_global_subprog_lock(void *ctx)
+{
+	volatile int ret = 0;
+
+	ret += global_subprog_lock(ret);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_subprog_unlock(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	ret += static_subprog_unlock(ctx);
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_global_subprog_unlock(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	ret += global_subprog_unlock(ret);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/recvmsg_unix_prog.c b/tools/testing/selftests/bpf/progs/recvmsg_unix_prog.c
index 4dfbc85525..1c7ab44bcc 100644
--- a/tools/testing/selftests/bpf/progs/recvmsg_unix_prog.c
+++ b/tools/testing/selftests/bpf/progs/recvmsg_unix_prog.c
@@ -27,8 +27,7 @@ int recvmsg_unix_prog(struct bpf_sock_addr *ctx)
 	if (sa_kern->uaddrlen != unaddrlen)
 		return 1;
 
-	sa_kern_unaddr = bpf_rdonly_cast(sa_kern->uaddr,
-						bpf_core_type_id_kernel(struct sockaddr_un));
+	sa_kern_unaddr = bpf_core_cast(sa_kern->uaddr, struct sockaddr_un);
 	if (memcmp(sa_kern_unaddr->sun_path, SERVUN_ADDRESS,
 			sizeof(SERVUN_ADDRESS) - 1) != 0)
 		return 1;
diff --git a/tools/testing/selftests/bpf/progs/sendmsg_unix_prog.c b/tools/testing/selftests/bpf/progs/sendmsg_unix_prog.c
index 1f67e83266..d8869b03dd 100644
--- a/tools/testing/selftests/bpf/progs/sendmsg_unix_prog.c
+++ b/tools/testing/selftests/bpf/progs/sendmsg_unix_prog.c
@@ -28,8 +28,7 @@ int sendmsg_unix_prog(struct bpf_sock_addr *ctx)
 	if (sa_kern->uaddrlen != unaddrlen)
 		return 0;
 
-	sa_kern_unaddr = bpf_rdonly_cast(sa_kern->uaddr,
-						bpf_core_type_id_kernel(struct sockaddr_un));
+	sa_kern_unaddr = bpf_core_cast(sa_kern->uaddr, struct sockaddr_un);
 	if (memcmp(sa_kern_unaddr->sun_path, SERVUN_REWRITE_ADDRESS,
 			sizeof(SERVUN_REWRITE_ADDRESS) - 1) != 0)
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c b/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c
index 3e745793b2..46d6eb2a3b 100644
--- a/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c
+++ b/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c
@@ -12,8 +12,6 @@ int cookie_found = 0;
 __u64 cookie = 0;
 __u32 omem = 0;
 
-void *bpf_rdonly_cast(void *, __u32) __ksym;
-
 struct {
 	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
 	__uint(map_flags, BPF_F_NO_PREALLOC);
@@ -29,7 +27,7 @@ int BPF_PROG(bpf_local_storage_destroy, struct bpf_local_storage *local_storage)
 	if (local_storage_ptr != local_storage)
 		return 0;
 
-	sk = bpf_rdonly_cast(sk_ptr, bpf_core_type_id_kernel(struct sock));
+	sk = bpf_core_cast(sk_ptr, struct sock);
 	if (sk->sk_cookie.counter != cookie)
 		return 0;
 
diff --git a/tools/testing/selftests/bpf/progs/sock_iter_batch.c b/tools/testing/selftests/bpf/progs/sock_iter_batch.c
index ffbbfe1fa1..96531b0d9d 100644
--- a/tools/testing/selftests/bpf/progs/sock_iter_batch.c
+++ b/tools/testing/selftests/bpf/progs/sock_iter_batch.c
@@ -32,7 +32,7 @@ int iter_tcp_soreuse(struct bpf_iter__tcp *ctx)
 	if (!sk)
 		return 0;
 
-	sk = bpf_rdonly_cast(sk, bpf_core_type_id_kernel(struct sock));
+	sk = bpf_core_cast(sk, struct sock);
 	if (sk->sk_family != AF_INET6 ||
 	    sk->sk_state != TCP_LISTEN ||
 	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr))
@@ -68,7 +68,7 @@ int iter_udp_soreuse(struct bpf_iter__udp *ctx)
 	if (!sk)
 		return 0;
 
-	sk = bpf_rdonly_cast(sk, bpf_core_type_id_kernel(struct sock));
+	sk = bpf_core_cast(sk, struct sock);
 	if (sk->sk_family != AF_INET6 ||
 	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr))
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h
index 40df2cc26e..f74459eead 100644
--- a/tools/testing/selftests/bpf/progs/strobemeta.h
+++ b/tools/testing/selftests/bpf/progs/strobemeta.h
@@ -10,6 +10,8 @@
 #include <linux/types.h>
 #include <bpf/bpf_helpers.h>
 
+#include "bpf_compiler.h"
+
 typedef uint32_t pid_t;
 struct task_struct {};
 
@@ -419,9 +421,9 @@ static __always_inline uint64_t read_map_var(struct strobemeta_cfg *cfg,
 	}
 
 #ifdef NO_UNROLL
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 #else
-#pragma unroll
+	__pragma_loop_unroll
 #endif
 	for (int i = 0; i < STROBE_MAX_MAP_ENTRIES; ++i) {
 		if (i >= map.cnt)
@@ -560,25 +562,25 @@ static void *read_strobe_meta(struct task_struct *task,
 		payload_off = sizeof(data->payload);
 #else
 #ifdef NO_UNROLL
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 #else
-#pragma unroll
+	__pragma_loop_unroll
 #endif /* NO_UNROLL */
 	for (int i = 0; i < STROBE_MAX_INTS; ++i) {
 		read_int_var(cfg, i, tls_base, &value, data);
 	}
 #ifdef NO_UNROLL
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 #else
-#pragma unroll
+	__pragma_loop_unroll
 #endif /* NO_UNROLL */
 	for (int i = 0; i < STROBE_MAX_STRS; ++i) {
 		payload_off = read_str_var(cfg, i, tls_base, &value, data, payload_off);
 	}
 #ifdef NO_UNROLL
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 #else
-#pragma unroll
+	__pragma_loop_unroll
 #endif /* NO_UNROLL */
 	for (int i = 0; i < STROBE_MAX_MAPS; ++i) {
 		payload_off = read_map_var(cfg, i, tls_base, &value, data, payload_off);
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_autocreate.c b/tools/testing/selftests/bpf/progs/struct_ops_autocreate.c
new file mode 100644
index 0000000000..ba10c38962
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_autocreate.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+int test_1_result = 0;
+
+SEC("struct_ops/test_1")
+int BPF_PROG(test_1)
+{
+	test_1_result = 42;
+	return 0;
+}
+
+SEC("struct_ops/test_1")
+int BPF_PROG(test_2)
+{
+	return 0;
+}
+
+struct bpf_testmod_ops___v1 {
+	int (*test_1)(void);
+};
+
+struct bpf_testmod_ops___v2 {
+	int (*test_1)(void);
+	int (*does_not_exist)(void);
+};
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops___v1 testmod_1 = {
+	.test_1 = (void *)test_1
+};
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops___v2 testmod_2 = {
+	.test_1 = (void *)test_1,
+	.does_not_exist = (void *)test_2
+};
+
+SEC("?.struct_ops")
+struct bpf_testmod_ops___v1 optional_map = {
+	.test_1 = (void *)test_1,
+};
+
+SEC("?.struct_ops.link")
+struct bpf_testmod_ops___v1 optional_map2 = {
+	.test_1 = (void *)test_1,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_autocreate2.c b/tools/testing/selftests/bpf/progs/struct_ops_autocreate2.c
new file mode 100644
index 0000000000..6049d9c902
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_autocreate2.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+int test_1_result = 0;
+
+SEC("?struct_ops/test_1")
+int BPF_PROG(foo)
+{
+	test_1_result = 42;
+	return 0;
+}
+
+SEC("?struct_ops/test_1")
+int BPF_PROG(bar)
+{
+	test_1_result = 24;
+	return 0;
+}
+
+struct bpf_testmod_ops {
+	int (*test_1)(void);
+};
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_1 = {
+	.test_1 = (void *)bar
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c
new file mode 100644
index 0000000000..b450f72e74
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../bpf_testmod/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+pid_t tgid = 0;
+
+/* This is a test BPF program that uses struct_ops to access an argument
+ * that may be NULL. This is a test for the verifier to ensure that it can
+ * rip PTR_MAYBE_NULL correctly.
+ */
+SEC("struct_ops/test_maybe_null")
+int BPF_PROG(test_maybe_null, int dummy,
+	     struct task_struct *task)
+{
+	if (task)
+		tgid = task->tgid;
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_1 = {
+	.test_maybe_null = (void *)test_maybe_null,
+};
+
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c
new file mode 100644
index 0000000000..6283099ec3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../bpf_testmod/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+pid_t tgid = 0;
+
+SEC("struct_ops/test_maybe_null_struct_ptr")
+int BPF_PROG(test_maybe_null_struct_ptr, int dummy,
+	     struct task_struct *task)
+{
+	tgid = task->tgid;
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_struct_ptr = {
+	.test_maybe_null = (void *)test_maybe_null_struct_ptr,
+};
+
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_module.c b/tools/testing/selftests/bpf/progs/struct_ops_module.c
new file mode 100644
index 0000000000..026cabfa7f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_module.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../bpf_testmod/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+int test_1_result = 0;
+int test_2_result = 0;
+
+SEC("struct_ops/test_1")
+int BPF_PROG(test_1)
+{
+	test_1_result = 0xdeadbeef;
+	return 0;
+}
+
+SEC("struct_ops/test_2")
+void BPF_PROG(test_2, int a, int b)
+{
+	test_2_result = a + b;
+}
+
+SEC("struct_ops/test_3")
+int BPF_PROG(test_3, int a, int b)
+{
+	test_2_result = a + b + 3;
+	return a + b + 3;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_1 = {
+	.test_1 = (void *)test_1,
+	.test_2 = (void *)test_2,
+	.data = 0x1,
+};
+
+SEC("struct_ops/test_2")
+void BPF_PROG(test_2_v2, int a, int b)
+{
+	test_2_result = a * b;
+}
+
+struct bpf_testmod_ops___v2 {
+	int (*test_1)(void);
+	void (*test_2)(int a, int b);
+	int (*test_maybe_null)(int dummy, struct task_struct *task);
+};
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops___v2 testmod_2 = {
+	.test_1 = (void *)test_1,
+	.test_2 = (void *)test_2_v2,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_multi_pages.c b/tools/testing/selftests/bpf/progs/struct_ops_multi_pages.c
new file mode 100644
index 0000000000..9efcc6e4d3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_multi_pages.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../bpf_testmod/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define TRAMP(x) \
+	SEC("struct_ops/tramp_" #x)		\
+	int BPF_PROG(tramp_ ## x, int a)	\
+	{					\
+		return a;			\
+	}
+
+TRAMP(1)
+TRAMP(2)
+TRAMP(3)
+TRAMP(4)
+TRAMP(5)
+TRAMP(6)
+TRAMP(7)
+TRAMP(8)
+TRAMP(9)
+TRAMP(10)
+TRAMP(11)
+TRAMP(12)
+TRAMP(13)
+TRAMP(14)
+TRAMP(15)
+TRAMP(16)
+TRAMP(17)
+TRAMP(18)
+TRAMP(19)
+TRAMP(20)
+TRAMP(21)
+TRAMP(22)
+TRAMP(23)
+TRAMP(24)
+TRAMP(25)
+TRAMP(26)
+TRAMP(27)
+TRAMP(28)
+TRAMP(29)
+TRAMP(30)
+TRAMP(31)
+TRAMP(32)
+TRAMP(33)
+TRAMP(34)
+TRAMP(35)
+TRAMP(36)
+TRAMP(37)
+TRAMP(38)
+TRAMP(39)
+TRAMP(40)
+
+#define F_TRAMP(x) .tramp_ ## x = (void *)tramp_ ## x
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops multi_pages = {
+	F_TRAMP(1),
+	F_TRAMP(2),
+	F_TRAMP(3),
+	F_TRAMP(4),
+	F_TRAMP(5),
+	F_TRAMP(6),
+	F_TRAMP(7),
+	F_TRAMP(8),
+	F_TRAMP(9),
+	F_TRAMP(10),
+	F_TRAMP(11),
+	F_TRAMP(12),
+	F_TRAMP(13),
+	F_TRAMP(14),
+	F_TRAMP(15),
+	F_TRAMP(16),
+	F_TRAMP(17),
+	F_TRAMP(18),
+	F_TRAMP(19),
+	F_TRAMP(20),
+	F_TRAMP(21),
+	F_TRAMP(22),
+	F_TRAMP(23),
+	F_TRAMP(24),
+	F_TRAMP(25),
+	F_TRAMP(26),
+	F_TRAMP(27),
+	F_TRAMP(28),
+	F_TRAMP(29),
+	F_TRAMP(30),
+	F_TRAMP(31),
+	F_TRAMP(32),
+	F_TRAMP(33),
+	F_TRAMP(34),
+	F_TRAMP(35),
+	F_TRAMP(36),
+	F_TRAMP(37),
+	F_TRAMP(38),
+	F_TRAMP(39),
+	F_TRAMP(40),
+};
diff --git a/tools/testing/selftests/bpf/progs/task_ls_recursion.c b/tools/testing/selftests/bpf/progs/task_ls_recursion.c
index 4542dc683b..f1853c38aa 100644
--- a/tools/testing/selftests/bpf/progs/task_ls_recursion.c
+++ b/tools/testing/selftests/bpf/progs/task_ls_recursion.c
@@ -27,23 +27,6 @@ struct {
 	__type(value, long);
 } map_b SEC(".maps");
 
-SEC("fentry/bpf_local_storage_lookup")
-int BPF_PROG(on_lookup)
-{
-	struct task_struct *task = bpf_get_current_task_btf();
-
-	if (!test_pid || task->pid != test_pid)
-		return 0;
-
-	/* The bpf_task_storage_delete will call
-	 * bpf_local_storage_lookup.  The prog->active will
-	 * stop the recursion.
-	 */
-	bpf_task_storage_delete(&map_a, task);
-	bpf_task_storage_delete(&map_b, task);
-	return 0;
-}
-
 SEC("fentry/bpf_local_storage_update")
 int BPF_PROG(on_update)
 {
diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
index 66b3049822..683c8aaa63 100644
--- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
@@ -20,8 +20,11 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+#include "bpf_compiler.h"
 #include "test_cls_redirect.h"
 
+#pragma GCC diagnostic ignored "-Waddress-of-packed-member"
+
 #ifdef SUBPROGS
 #define INLINING __noinline
 #else
@@ -267,7 +270,7 @@ static INLINING void pkt_ipv4_checksum(struct iphdr *iph)
 	uint32_t acc = 0;
 	uint16_t *ipw = (uint16_t *)iph;
 
-#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (size_t i = 0; i < sizeof(struct iphdr) / 2; i++) {
 		acc += ipw[i];
 	}
@@ -294,7 +297,7 @@ bool pkt_skip_ipv6_extension_headers(buf_t *pkt,
 	};
 	*is_fragment = false;
 
-#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (int i = 0; i < 6; i++) {
 		switch (exthdr.next) {
 		case IPPROTO_FRAGMENT:
diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c b/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c
index f41c81212e..da54c09e9a 100644
--- a/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c
@@ -23,6 +23,8 @@
 #include "test_cls_redirect.h"
 #include "bpf_kfuncs.h"
 
+#pragma GCC diagnostic ignored "-Waddress-of-packed-member"
+
 #define offsetofend(TYPE, MEMBER) \
 	(offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER)))
 
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c b/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c
index 22aba3f6e3..6fc8b9d66e 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c
@@ -80,7 +80,7 @@ int test_core_type_id(void *ctx)
 	 * to detect whether this test has to be executed, however strange
 	 * that might look like.
 	 *
-	 *   [0] https://reviews.llvm.org/D85174
+	 *   [0] https://github.com/llvm/llvm-project/commit/00602ee7ef0bf6c68d690a2bd729c12b95c95c99
 	 */
 #if __has_builtin(__builtin_preserve_type_info)
 	struct core_reloc_type_id_output *out = (void *)&data.out;
diff --git a/tools/testing/selftests/bpf/progs/test_fill_link_info.c b/tools/testing/selftests/bpf/progs/test_fill_link_info.c
index 69509f8bb6..6afa834756 100644
--- a/tools/testing/selftests/bpf/progs/test_fill_link_info.c
+++ b/tools/testing/selftests/bpf/progs/test_fill_link_info.c
@@ -33,6 +33,12 @@ int BPF_PROG(tp_run)
 	return 0;
 }
 
+SEC("perf_event")
+int event_run(void *ctx)
+{
+	return 0;
+}
+
 SEC("kprobe.multi")
 int BPF_PROG(kmulti_run)
 {
diff --git a/tools/testing/selftests/bpf/progs/test_global_func1.c b/tools/testing/selftests/bpf/progs/test_global_func1.c
index 17a9f59bf5..fc69ff1888 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func1.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func1.c
@@ -5,7 +5,7 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
-#define MAX_STACK (512 - 3 * 32 + 8)
+#define MAX_STACK 260
 
 static __attribute__ ((noinline))
 int f0(int var, struct __sk_buff *skb)
@@ -30,6 +30,10 @@ int f3(int, struct __sk_buff *skb, int);
 __attribute__ ((noinline))
 int f2(int val, struct __sk_buff *skb)
 {
+	volatile char buf[MAX_STACK] = {};
+
+	__sink(buf[MAX_STACK - 1]);
+
 	return f1(skb) + f3(val, skb, 1);
 }
 
@@ -44,7 +48,7 @@ int f3(int val, struct __sk_buff *skb, int var)
 }
 
 SEC("tc")
-__failure __msg("combined stack size of 4 calls is 544")
+__failure __msg("combined stack size of 3 calls is")
 int global_func1(struct __sk_buff *skb)
 {
 	return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4);
diff --git a/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c b/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c
index 9a06e5eb1f..143c8a4852 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c
@@ -26,6 +26,23 @@ int kprobe_typedef_ctx(void *ctx)
 	return kprobe_typedef_ctx_subprog(ctx);
 }
 
+/* s390x defines:
+ *
+ * typedef user_pt_regs bpf_user_pt_regs_t;
+ * typedef struct { ... } user_pt_regs;
+ *
+ * And so "canonical" underlying struct type is anonymous.
+ * So on s390x only valid ways to have PTR_TO_CTX argument in global subprogs
+ * are:
+ *   - bpf_user_pt_regs_t *ctx (typedef);
+ *   - struct bpf_user_pt_regs_t *ctx (backwards compatible struct hack);
+ *   - void *ctx __arg_ctx (arg:ctx tag)
+ *
+ * Other architectures also allow using underlying struct types (e.g.,
+ * `struct pt_regs *ctx` for x86-64)
+ */
+#ifndef bpf_target_s390
+
 #define pt_regs_struct_t typeof(*(__PT_REGS_CAST((struct pt_regs *)NULL)))
 
 __weak int kprobe_struct_ctx_subprog(pt_regs_struct_t *ctx)
@@ -40,6 +57,8 @@ int kprobe_resolved_ctx(void *ctx)
 	return kprobe_struct_ctx_subprog(ctx);
 }
 
+#endif
+
 /* this is current hack to make this work on old kernels */
 struct bpf_user_pt_regs_t {};
 
diff --git a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
index 48ff2b2ad5..fed66f36ad 100644
--- a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
+++ b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
@@ -6,6 +6,8 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+#include "bpf_compiler.h"
+
 /* Packet parsing state machine helpers. */
 #define cursor_advance(_cursor, _len) \
 	({ void *_tmp = _cursor; _cursor += _len; _tmp; })
@@ -131,7 +133,7 @@ int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh,
 	*pad_off = 0;
 
 	// we can only go as far as ~10 TLVs due to the BPF max stack size
-	#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (int i = 0; i < 10; i++) {
 		struct sr6_tlv_t tlv;
 
@@ -302,7 +304,7 @@ int __encap_srh(struct __sk_buff *skb)
 
 	seg = (struct ip6_addr_t *)((char *)srh + sizeof(*srh));
 
-	#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (unsigned long long lo = 0; lo < 4; lo++) {
 		seg->lo = bpf_cpu_to_be64(4 - lo);
 		seg->hi = bpf_cpu_to_be64(hi);
diff --git a/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c b/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c
index 4bdd65b5aa..2fdc44e766 100644
--- a/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c
+++ b/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c
@@ -6,13 +6,13 @@
 
 char tp_name[128];
 
-SEC("lsm/bpf")
+SEC("lsm.s/bpf")
 int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size)
 {
 	switch (cmd) {
 	case BPF_RAW_TRACEPOINT_OPEN:
-		bpf_probe_read_user_str(tp_name, sizeof(tp_name) - 1,
-					(void *)attr->raw_tracepoint.name);
+		bpf_copy_from_user(tp_name, sizeof(tp_name) - 1,
+				   (void *)attr->raw_tracepoint.name);
 		break;
 	default:
 		break;
diff --git a/tools/testing/selftests/bpf/progs/test_seg6_loop.c b/tools/testing/selftests/bpf/progs/test_seg6_loop.c
index a7278f0643..5059050f74 100644
--- a/tools/testing/selftests/bpf/progs/test_seg6_loop.c
+++ b/tools/testing/selftests/bpf/progs/test_seg6_loop.c
@@ -6,6 +6,8 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+#include "bpf_compiler.h"
+
 /* Packet parsing state machine helpers. */
 #define cursor_advance(_cursor, _len) \
 	({ void *_tmp = _cursor; _cursor += _len; _tmp; })
@@ -134,7 +136,7 @@ static __always_inline int is_valid_tlv_boundary(struct __sk_buff *skb,
 	// we can only go as far as ~10 TLVs due to the BPF max stack size
 	// workaround: define induction variable "i" as "long" instead
 	// of "int" to prevent alu32 sub-register spilling.
-	#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 	for (long i = 0; i < 100; i++) {
 		struct sr6_tlv_t tlv;
 
diff --git a/tools/testing/selftests/bpf/progs/test_siphash.h b/tools/testing/selftests/bpf/progs/test_siphash.h
new file mode 100644
index 0000000000..5d3a7ec367
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_siphash.h
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#ifndef _TEST_SIPHASH_H
+#define _TEST_SIPHASH_H
+
+/* include/linux/bitops.h */
+static inline u64 rol64(u64 word, unsigned int shift)
+{
+	return (word << (shift & 63)) | (word >> ((-shift) & 63));
+}
+
+/* include/linux/siphash.h */
+#define SIPHASH_PERMUTATION(a, b, c, d) ( \
+	(a) += (b), (b) = rol64((b), 13), (b) ^= (a), (a) = rol64((a), 32), \
+	(c) += (d), (d) = rol64((d), 16), (d) ^= (c), \
+	(a) += (d), (d) = rol64((d), 21), (d) ^= (a), \
+	(c) += (b), (b) = rol64((b), 17), (b) ^= (c), (c) = rol64((c), 32))
+
+#define SIPHASH_CONST_0 0x736f6d6570736575ULL
+#define SIPHASH_CONST_1 0x646f72616e646f6dULL
+#define SIPHASH_CONST_2 0x6c7967656e657261ULL
+#define SIPHASH_CONST_3 0x7465646279746573ULL
+
+/* lib/siphash.c */
+#define SIPROUND SIPHASH_PERMUTATION(v0, v1, v2, v3)
+
+#define PREAMBLE(len) \
+	u64 v0 = SIPHASH_CONST_0; \
+	u64 v1 = SIPHASH_CONST_1; \
+	u64 v2 = SIPHASH_CONST_2; \
+	u64 v3 = SIPHASH_CONST_3; \
+	u64 b = ((u64)(len)) << 56; \
+	v3 ^= key->key[1]; \
+	v2 ^= key->key[0]; \
+	v1 ^= key->key[1]; \
+	v0 ^= key->key[0];
+
+#define POSTAMBLE \
+	v3 ^= b; \
+	SIPROUND; \
+	SIPROUND; \
+	v0 ^= b; \
+	v2 ^= 0xff; \
+	SIPROUND; \
+	SIPROUND; \
+	SIPROUND; \
+	SIPROUND; \
+	return (v0 ^ v1) ^ (v2 ^ v3);
+
+static inline u64 siphash_2u64(const u64 first, const u64 second, const siphash_key_t *key)
+{
+	PREAMBLE(16)
+	v3 ^= first;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= first;
+	v3 ^= second;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= second;
+	POSTAMBLE
+}
+#endif
diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
index c482110cfc..a724a70c67 100644
--- a/tools/testing/selftests/bpf/progs/test_skb_ctx.c
+++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
@@ -3,12 +3,14 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
+#include "bpf_compiler.h"
+
 char _license[] SEC("license") = "GPL";
 
 SEC("tc")
 int process(struct __sk_buff *skb)
 {
-	#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (int i = 0; i < 5; i++) {
 		if (skb->cb[i] != i + 1)
 			return 1;
diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock.c b/tools/testing/selftests/bpf/progs/test_spin_lock.c
index b2440a0ff4..d8d77bdffd 100644
--- a/tools/testing/selftests/bpf/progs/test_spin_lock.c
+++ b/tools/testing/selftests/bpf/progs/test_spin_lock.c
@@ -101,4 +101,69 @@ int bpf_spin_lock_test(struct __sk_buff *skb)
 err:
 	return err;
 }
+
+struct bpf_spin_lock lockA __hidden SEC(".data.A");
+
+__noinline
+static int static_subprog(struct __sk_buff *ctx)
+{
+	volatile int ret = 0;
+
+	if (ctx->protocol)
+		return ret;
+	return ret + ctx->len;
+}
+
+__noinline
+static int static_subprog_lock(struct __sk_buff *ctx)
+{
+	volatile int ret = 0;
+
+	ret = static_subprog(ctx);
+	bpf_spin_lock(&lockA);
+	return ret + ctx->len;
+}
+
+__noinline
+static int static_subprog_unlock(struct __sk_buff *ctx)
+{
+	volatile int ret = 0;
+
+	ret = static_subprog(ctx);
+	bpf_spin_unlock(&lockA);
+	return ret + ctx->len;
+}
+
+SEC("tc")
+int lock_static_subprog_call(struct __sk_buff *ctx)
+{
+	int ret = 0;
+
+	bpf_spin_lock(&lockA);
+	if (ctx->mark == 42)
+		ret = static_subprog(ctx);
+	bpf_spin_unlock(&lockA);
+	return ret;
+}
+
+SEC("tc")
+int lock_static_subprog_lock(struct __sk_buff *ctx)
+{
+	int ret = 0;
+
+	ret = static_subprog_lock(ctx);
+	bpf_spin_unlock(&lockA);
+	return ret;
+}
+
+SEC("tc")
+int lock_static_subprog_unlock(struct __sk_buff *ctx)
+{
+	int ret = 0;
+
+	bpf_spin_lock(&lockA);
+	ret = static_subprog_unlock(ctx);
+	return ret;
+}
+
 char _license[] SEC("license") = "GPL";
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 86cd183ef6..43f40c4fe2 100644
--- a/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c
+++ b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c
@@ -201,4 +201,48 @@ CHECK(innermapval_mapval, &iv->lock, &v->lock);
 
 #undef CHECK
 
+__noinline
+int global_subprog(struct __sk_buff *ctx)
+{
+	volatile int ret = 0;
+
+	if (ctx->protocol)
+		ret += ctx->protocol;
+	return ret + ctx->mark;
+}
+
+__noinline
+static int static_subprog_call_global(struct __sk_buff *ctx)
+{
+	volatile int ret = 0;
+
+	if (ctx->protocol)
+		return ret;
+	return ret + ctx->len + global_subprog(ctx);
+}
+
+SEC("?tc")
+int lock_global_subprog_call1(struct __sk_buff *ctx)
+{
+	int ret = 0;
+
+	bpf_spin_lock(&lockA);
+	if (ctx->mark == 42)
+		ret = global_subprog(ctx);
+	bpf_spin_unlock(&lockA);
+	return ret;
+}
+
+SEC("?tc")
+int lock_global_subprog_call2(struct __sk_buff *ctx)
+{
+	int ret = 0;
+
+	bpf_spin_lock(&lockA);
+	if (ctx->mark == 42)
+		ret = static_subprog_call_global(ctx);
+	bpf_spin_unlock(&lockA);
+	return ret;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
index 553a282d81..7f74077d66 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
@@ -9,6 +9,8 @@
 
 #include <bpf/bpf_helpers.h>
 
+#include "bpf_compiler.h"
+
 #ifndef ARRAY_SIZE
 #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
 #endif
@@ -30,7 +32,7 @@ static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx)
 	if (ret < 0 || ret != sizeof(tcp_mem_name) - 1)
 		return 0;
 
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 	for (i = 0; i < sizeof(tcp_mem_name); ++i)
 		if (name[i] != tcp_mem_name[i])
 			return 0;
@@ -59,7 +61,7 @@ int sysctl_tcp_mem(struct bpf_sysctl *ctx)
 	if (ret < 0 || ret >= MAX_VALUE_STR_LEN)
 		return 0;
 
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 	for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) {
 		ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0,
 				  tcp_mem + i);
diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c
index 2b64bc563a..68a75436e8 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c
@@ -9,6 +9,8 @@
 
 #include <bpf/bpf_helpers.h>
 
+#include "bpf_compiler.h"
+
 #ifndef ARRAY_SIZE
 #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
 #endif
@@ -30,7 +32,7 @@ static __attribute__((noinline)) int is_tcp_mem(struct bpf_sysctl *ctx)
 	if (ret < 0 || ret != sizeof(tcp_mem_name) - 1)
 		return 0;
 
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 	for (i = 0; i < sizeof(tcp_mem_name); ++i)
 		if (name[i] != tcp_mem_name[i])
 			return 0;
@@ -57,7 +59,7 @@ int sysctl_tcp_mem(struct bpf_sysctl *ctx)
 	if (ret < 0 || ret >= MAX_VALUE_STR_LEN)
 		return 0;
 
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 	for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) {
 		ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0,
 				  tcp_mem + i);
diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
index 5489823c83..efc3c61f78 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
@@ -9,6 +9,8 @@
 
 #include <bpf/bpf_helpers.h>
 
+#include "bpf_compiler.h"
+
 /* Max supported length of a string with unsigned long in base 10 (pow2 - 1). */
 #define MAX_ULONG_STR_LEN 0xF
 
@@ -31,7 +33,7 @@ static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx)
 	if (ret < 0 || ret != sizeof(tcp_mem_name) - 1)
 		return 0;
 
-#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (i = 0; i < sizeof(tcp_mem_name); ++i)
 		if (name[i] != tcp_mem_name[i])
 			return 0;
@@ -57,7 +59,7 @@ int sysctl_tcp_mem(struct bpf_sysctl *ctx)
 	if (ret < 0 || ret >= MAX_VALUE_STR_LEN)
 		return 0;
 
-#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) {
 		ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0,
 				  tcp_mem + i);
diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
index e6e678aa98..404124a938 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
@@ -19,6 +19,9 @@
 
 #include <bpf/bpf_endian.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_compiler.h"
+
+#pragma GCC diagnostic ignored "-Waddress-of-packed-member"
 
 static const int cfg_port = 8000;
 
@@ -81,7 +84,7 @@ static __always_inline void set_ipv4_csum(struct iphdr *iph)
 
 	iph->check = 0;
 
-#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (i = 0, csum = 0; i < sizeof(*iph) >> 1; i++)
 		csum += *iph16++;
 
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c
new file mode 100644
index 0000000000..c8e4553648
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c
@@ -0,0 +1,595 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#include "vmlinux.h"
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include "bpf_tracing_net.h"
+#include "bpf_kfuncs.h"
+#include "test_siphash.h"
+#include "test_tcp_custom_syncookie.h"
+
+#define MAX_PACKET_OFF 0xffff
+
+/* Hash is calculated for each client and split into ISN and TS.
+ *
+ *       MSB                                   LSB
+ * ISN:  | 31 ... 8 | 7 6 |   5 |    4 | 3 2 1 0 |
+ *       |   Hash_1 | MSS | ECN | SACK |  WScale |
+ *
+ * TS:   | 31 ... 8 |          7 ... 0           |
+ *       |   Random |           Hash_2           |
+ */
+#define COOKIE_BITS	8
+#define COOKIE_MASK	(((__u32)1 << COOKIE_BITS) - 1)
+
+enum {
+	/* 0xf is invalid thus means that SYN did not have WScale. */
+	BPF_SYNCOOKIE_WSCALE_MASK	= (1 << 4) - 1,
+	BPF_SYNCOOKIE_SACK		= (1 << 4),
+	BPF_SYNCOOKIE_ECN		= (1 << 5),
+};
+
+#define MSS_LOCAL_IPV4	65495
+#define MSS_LOCAL_IPV6	65476
+
+const __u16 msstab4[] = {
+	536,
+	1300,
+	1460,
+	MSS_LOCAL_IPV4,
+};
+
+const __u16 msstab6[] = {
+	1280 - 60, /* IPV6_MIN_MTU - 60 */
+	1480 - 60,
+	9000 - 60,
+	MSS_LOCAL_IPV6,
+};
+
+static siphash_key_t test_key_siphash = {
+	{ 0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL }
+};
+
+struct tcp_syncookie {
+	struct __sk_buff *skb;
+	void *data;
+	void *data_end;
+	struct ethhdr *eth;
+	struct iphdr *ipv4;
+	struct ipv6hdr *ipv6;
+	struct tcphdr *tcp;
+	__be32 *ptr32;
+	struct bpf_tcp_req_attrs attrs;
+	u32 off;
+	u32 cookie;
+	u64 first;
+};
+
+bool handled_syn, handled_ack;
+
+static int tcp_load_headers(struct tcp_syncookie *ctx)
+{
+	ctx->data = (void *)(long)ctx->skb->data;
+	ctx->data_end = (void *)(long)ctx->skb->data_end;
+	ctx->eth = (struct ethhdr *)(long)ctx->skb->data;
+
+	if (ctx->eth + 1 > ctx->data_end)
+		goto err;
+
+	switch (bpf_ntohs(ctx->eth->h_proto)) {
+	case ETH_P_IP:
+		ctx->ipv4 = (struct iphdr *)(ctx->eth + 1);
+
+		if (ctx->ipv4 + 1 > ctx->data_end)
+			goto err;
+
+		if (ctx->ipv4->ihl != sizeof(*ctx->ipv4) / 4)
+			goto err;
+
+		if (ctx->ipv4->version != 4)
+			goto err;
+
+		if (ctx->ipv4->protocol != IPPROTO_TCP)
+			goto err;
+
+		ctx->tcp = (struct tcphdr *)(ctx->ipv4 + 1);
+		break;
+	case ETH_P_IPV6:
+		ctx->ipv6 = (struct ipv6hdr *)(ctx->eth + 1);
+
+		if (ctx->ipv6 + 1 > ctx->data_end)
+			goto err;
+
+		if (ctx->ipv6->version != 6)
+			goto err;
+
+		if (ctx->ipv6->nexthdr != NEXTHDR_TCP)
+			goto err;
+
+		ctx->tcp = (struct tcphdr *)(ctx->ipv6 + 1);
+		break;
+	default:
+		goto err;
+	}
+
+	if (ctx->tcp + 1 > ctx->data_end)
+		goto err;
+
+	return 0;
+err:
+	return -1;
+}
+
+static int tcp_reload_headers(struct tcp_syncookie *ctx)
+{
+	/* Without volatile,
+	 * R3 32-bit pointer arithmetic prohibited
+	 */
+	volatile u64 data_len = ctx->skb->data_end - ctx->skb->data;
+
+	if (ctx->tcp->doff < sizeof(*ctx->tcp) / 4)
+		goto err;
+
+	/* Needed to calculate csum and parse TCP options. */
+	if (bpf_skb_change_tail(ctx->skb, data_len + 60 - ctx->tcp->doff * 4, 0))
+		goto err;
+
+	ctx->data = (void *)(long)ctx->skb->data;
+	ctx->data_end = (void *)(long)ctx->skb->data_end;
+	ctx->eth = (struct ethhdr *)(long)ctx->skb->data;
+	if (ctx->ipv4) {
+		ctx->ipv4 = (struct iphdr *)(ctx->eth + 1);
+		ctx->ipv6 = NULL;
+		ctx->tcp = (struct tcphdr *)(ctx->ipv4 + 1);
+	} else {
+		ctx->ipv4 = NULL;
+		ctx->ipv6 = (struct ipv6hdr *)(ctx->eth + 1);
+		ctx->tcp = (struct tcphdr *)(ctx->ipv6 + 1);
+	}
+
+	if ((void *)ctx->tcp + 60 > ctx->data_end)
+		goto err;
+
+	return 0;
+err:
+	return -1;
+}
+
+static __sum16 tcp_v4_csum(struct tcp_syncookie *ctx, __wsum csum)
+{
+	return csum_tcpudp_magic(ctx->ipv4->saddr, ctx->ipv4->daddr,
+				 ctx->tcp->doff * 4, IPPROTO_TCP, csum);
+}
+
+static __sum16 tcp_v6_csum(struct tcp_syncookie *ctx, __wsum csum)
+{
+	return csum_ipv6_magic(&ctx->ipv6->saddr, &ctx->ipv6->daddr,
+			       ctx->tcp->doff * 4, IPPROTO_TCP, csum);
+}
+
+static int tcp_validate_header(struct tcp_syncookie *ctx)
+{
+	s64 csum;
+
+	if (tcp_reload_headers(ctx))
+		goto err;
+
+	csum = bpf_csum_diff(0, 0, (void *)ctx->tcp, ctx->tcp->doff * 4, 0);
+	if (csum < 0)
+		goto err;
+
+	if (ctx->ipv4) {
+		/* check tcp_v4_csum(csum) is 0 if not on lo. */
+
+		csum = bpf_csum_diff(0, 0, (void *)ctx->ipv4, ctx->ipv4->ihl * 4, 0);
+		if (csum < 0)
+			goto err;
+
+		if (csum_fold(csum) != 0)
+			goto err;
+	} else if (ctx->ipv6) {
+		/* check tcp_v6_csum(csum) is 0 if not on lo. */
+	}
+
+	return 0;
+err:
+	return -1;
+}
+
+static __always_inline void *next(struct tcp_syncookie *ctx, __u32 sz)
+{
+	__u64 off = ctx->off;
+	__u8 *data;
+
+	/* Verifier forbids access to packet when offset exceeds MAX_PACKET_OFF */
+	if (off > MAX_PACKET_OFF - sz)
+		return NULL;
+
+	data = ctx->data + off;
+	barrier_var(data);
+	if (data + sz >= ctx->data_end)
+		return NULL;
+
+	ctx->off += sz;
+	return data;
+}
+
+static int tcp_parse_option(__u32 index, struct tcp_syncookie *ctx)
+{
+	__u8 *opcode, *opsize, *wscale;
+	__u32 *tsval, *tsecr;
+	__u16 *mss;
+	__u32 off;
+
+	off = ctx->off;
+	opcode = next(ctx, 1);
+	if (!opcode)
+		goto stop;
+
+	if (*opcode == TCPOPT_EOL)
+		goto stop;
+
+	if (*opcode == TCPOPT_NOP)
+		goto next;
+
+	opsize = next(ctx, 1);
+	if (!opsize)
+		goto stop;
+
+	if (*opsize < 2)
+		goto stop;
+
+	switch (*opcode) {
+	case TCPOPT_MSS:
+		mss = next(ctx, 2);
+		if (*opsize == TCPOLEN_MSS && ctx->tcp->syn && mss)
+			ctx->attrs.mss = get_unaligned_be16(mss);
+		break;
+	case TCPOPT_WINDOW:
+		wscale = next(ctx, 1);
+		if (*opsize == TCPOLEN_WINDOW && ctx->tcp->syn && wscale) {
+			ctx->attrs.wscale_ok = 1;
+			ctx->attrs.snd_wscale = *wscale;
+		}
+		break;
+	case TCPOPT_TIMESTAMP:
+		tsval = next(ctx, 4);
+		tsecr = next(ctx, 4);
+		if (*opsize == TCPOLEN_TIMESTAMP && tsval && tsecr) {
+			ctx->attrs.rcv_tsval = get_unaligned_be32(tsval);
+			ctx->attrs.rcv_tsecr = get_unaligned_be32(tsecr);
+
+			if (ctx->tcp->syn && ctx->attrs.rcv_tsecr)
+				ctx->attrs.tstamp_ok = 0;
+			else
+				ctx->attrs.tstamp_ok = 1;
+		}
+		break;
+	case TCPOPT_SACK_PERM:
+		if (*opsize == TCPOLEN_SACK_PERM && ctx->tcp->syn)
+			ctx->attrs.sack_ok = 1;
+		break;
+	}
+
+	ctx->off = off + *opsize;
+next:
+	return 0;
+stop:
+	return 1;
+}
+
+static void tcp_parse_options(struct tcp_syncookie *ctx)
+{
+	ctx->off = (__u8 *)(ctx->tcp + 1) - (__u8 *)ctx->data,
+
+	bpf_loop(40, tcp_parse_option, ctx, 0);
+}
+
+static int tcp_validate_sysctl(struct tcp_syncookie *ctx)
+{
+	if ((ctx->ipv4 && ctx->attrs.mss != MSS_LOCAL_IPV4) ||
+	    (ctx->ipv6 && ctx->attrs.mss != MSS_LOCAL_IPV6))
+		goto err;
+
+	if (!ctx->attrs.wscale_ok || ctx->attrs.snd_wscale != 7)
+		goto err;
+
+	if (!ctx->attrs.tstamp_ok)
+		goto err;
+
+	if (!ctx->attrs.sack_ok)
+		goto err;
+
+	if (!ctx->tcp->ece || !ctx->tcp->cwr)
+		goto err;
+
+	return 0;
+err:
+	return -1;
+}
+
+static void tcp_prepare_cookie(struct tcp_syncookie *ctx)
+{
+	u32 seq = bpf_ntohl(ctx->tcp->seq);
+	u64 first = 0, second;
+	int mssind = 0;
+	u32 hash;
+
+	if (ctx->ipv4) {
+		for (mssind = ARRAY_SIZE(msstab4) - 1; mssind; mssind--)
+			if (ctx->attrs.mss >= msstab4[mssind])
+				break;
+
+		ctx->attrs.mss = msstab4[mssind];
+
+		first = (u64)ctx->ipv4->saddr << 32 | ctx->ipv4->daddr;
+	} else if (ctx->ipv6) {
+		for (mssind = ARRAY_SIZE(msstab6) - 1; mssind; mssind--)
+			if (ctx->attrs.mss >= msstab6[mssind])
+				break;
+
+		ctx->attrs.mss = msstab6[mssind];
+
+		first = (u64)ctx->ipv6->saddr.in6_u.u6_addr8[0] << 32 |
+			ctx->ipv6->daddr.in6_u.u6_addr32[0];
+	}
+
+	second = (u64)seq << 32 | ctx->tcp->source << 16 | ctx->tcp->dest;
+	hash = siphash_2u64(first, second, &test_key_siphash);
+
+	if (ctx->attrs.tstamp_ok) {
+		ctx->attrs.rcv_tsecr = bpf_get_prandom_u32();
+		ctx->attrs.rcv_tsecr &= ~COOKIE_MASK;
+		ctx->attrs.rcv_tsecr |= hash & COOKIE_MASK;
+	}
+
+	hash &= ~COOKIE_MASK;
+	hash |= mssind << 6;
+
+	if (ctx->attrs.wscale_ok)
+		hash |= ctx->attrs.snd_wscale & BPF_SYNCOOKIE_WSCALE_MASK;
+
+	if (ctx->attrs.sack_ok)
+		hash |= BPF_SYNCOOKIE_SACK;
+
+	if (ctx->attrs.tstamp_ok && ctx->tcp->ece && ctx->tcp->cwr)
+		hash |= BPF_SYNCOOKIE_ECN;
+
+	ctx->cookie = hash;
+}
+
+static void tcp_write_options(struct tcp_syncookie *ctx)
+{
+	ctx->ptr32 = (__be32 *)(ctx->tcp + 1);
+
+	*ctx->ptr32++ = bpf_htonl(TCPOPT_MSS << 24 | TCPOLEN_MSS << 16 |
+				  ctx->attrs.mss);
+
+	if (ctx->attrs.wscale_ok)
+		*ctx->ptr32++ = bpf_htonl(TCPOPT_NOP << 24 |
+					  TCPOPT_WINDOW << 16 |
+					  TCPOLEN_WINDOW << 8 |
+					  ctx->attrs.snd_wscale);
+
+	if (ctx->attrs.tstamp_ok) {
+		if (ctx->attrs.sack_ok)
+			*ctx->ptr32++ = bpf_htonl(TCPOPT_SACK_PERM << 24 |
+						  TCPOLEN_SACK_PERM << 16 |
+						  TCPOPT_TIMESTAMP << 8 |
+						  TCPOLEN_TIMESTAMP);
+		else
+			*ctx->ptr32++ = bpf_htonl(TCPOPT_NOP << 24 |
+						  TCPOPT_NOP << 16 |
+						  TCPOPT_TIMESTAMP << 8 |
+						  TCPOLEN_TIMESTAMP);
+
+		*ctx->ptr32++ = bpf_htonl(ctx->attrs.rcv_tsecr);
+		*ctx->ptr32++ = bpf_htonl(ctx->attrs.rcv_tsval);
+	} else if (ctx->attrs.sack_ok) {
+		*ctx->ptr32++ = bpf_htonl(TCPOPT_NOP << 24 |
+					  TCPOPT_NOP << 16 |
+					  TCPOPT_SACK_PERM << 8 |
+					  TCPOLEN_SACK_PERM);
+	}
+}
+
+static int tcp_handle_syn(struct tcp_syncookie *ctx)
+{
+	s64 csum;
+
+	if (tcp_validate_header(ctx))
+		goto err;
+
+	tcp_parse_options(ctx);
+
+	if (tcp_validate_sysctl(ctx))
+		goto err;
+
+	tcp_prepare_cookie(ctx);
+	tcp_write_options(ctx);
+
+	swap(ctx->tcp->source, ctx->tcp->dest);
+	ctx->tcp->check = 0;
+	ctx->tcp->ack_seq = bpf_htonl(bpf_ntohl(ctx->tcp->seq) + 1);
+	ctx->tcp->seq = bpf_htonl(ctx->cookie);
+	ctx->tcp->doff = ((long)ctx->ptr32 - (long)ctx->tcp) >> 2;
+	ctx->tcp->ack = 1;
+	if (!ctx->attrs.tstamp_ok || !ctx->tcp->ece || !ctx->tcp->cwr)
+		ctx->tcp->ece = 0;
+	ctx->tcp->cwr = 0;
+
+	csum = bpf_csum_diff(0, 0, (void *)ctx->tcp, ctx->tcp->doff * 4, 0);
+	if (csum < 0)
+		goto err;
+
+	if (ctx->ipv4) {
+		swap(ctx->ipv4->saddr, ctx->ipv4->daddr);
+		ctx->tcp->check = tcp_v4_csum(ctx, csum);
+
+		ctx->ipv4->check = 0;
+		ctx->ipv4->tos = 0;
+		ctx->ipv4->tot_len = bpf_htons((long)ctx->ptr32 - (long)ctx->ipv4);
+		ctx->ipv4->id = 0;
+		ctx->ipv4->ttl = 64;
+
+		csum = bpf_csum_diff(0, 0, (void *)ctx->ipv4, sizeof(*ctx->ipv4), 0);
+		if (csum < 0)
+			goto err;
+
+		ctx->ipv4->check = csum_fold(csum);
+	} else if (ctx->ipv6) {
+		swap(ctx->ipv6->saddr, ctx->ipv6->daddr);
+		ctx->tcp->check = tcp_v6_csum(ctx, csum);
+
+		*(__be32 *)ctx->ipv6 = bpf_htonl(0x60000000);
+		ctx->ipv6->payload_len = bpf_htons((long)ctx->ptr32 - (long)ctx->tcp);
+		ctx->ipv6->hop_limit = 64;
+	}
+
+	swap_array(ctx->eth->h_source, ctx->eth->h_dest);
+
+	if (bpf_skb_change_tail(ctx->skb, (long)ctx->ptr32 - (long)ctx->eth, 0))
+		goto err;
+
+	return bpf_redirect(ctx->skb->ifindex, 0);
+err:
+	return TC_ACT_SHOT;
+}
+
+static int tcp_validate_cookie(struct tcp_syncookie *ctx)
+{
+	u32 cookie = bpf_ntohl(ctx->tcp->ack_seq) - 1;
+	u32 seq = bpf_ntohl(ctx->tcp->seq) - 1;
+	u64 first = 0, second;
+	int mssind;
+	u32 hash;
+
+	if (ctx->ipv4)
+		first = (u64)ctx->ipv4->saddr << 32 | ctx->ipv4->daddr;
+	else if (ctx->ipv6)
+		first = (u64)ctx->ipv6->saddr.in6_u.u6_addr8[0] << 32 |
+			ctx->ipv6->daddr.in6_u.u6_addr32[0];
+
+	second = (u64)seq << 32 | ctx->tcp->source << 16 | ctx->tcp->dest;
+	hash = siphash_2u64(first, second, &test_key_siphash);
+
+	if (ctx->attrs.tstamp_ok)
+		hash -= ctx->attrs.rcv_tsecr & COOKIE_MASK;
+	else
+		hash &= ~COOKIE_MASK;
+
+	hash -= cookie & ~COOKIE_MASK;
+	if (hash)
+		goto err;
+
+	mssind = (cookie & (3 << 6)) >> 6;
+	if (ctx->ipv4) {
+		if (mssind > ARRAY_SIZE(msstab4))
+			goto err;
+
+		ctx->attrs.mss = msstab4[mssind];
+	} else {
+		if (mssind > ARRAY_SIZE(msstab6))
+			goto err;
+
+		ctx->attrs.mss = msstab6[mssind];
+	}
+
+	ctx->attrs.snd_wscale = cookie & BPF_SYNCOOKIE_WSCALE_MASK;
+	ctx->attrs.rcv_wscale = ctx->attrs.snd_wscale;
+	ctx->attrs.wscale_ok = ctx->attrs.snd_wscale == BPF_SYNCOOKIE_WSCALE_MASK;
+	ctx->attrs.sack_ok = cookie & BPF_SYNCOOKIE_SACK;
+	ctx->attrs.ecn_ok = cookie & BPF_SYNCOOKIE_ECN;
+
+	return 0;
+err:
+	return -1;
+}
+
+static int tcp_handle_ack(struct tcp_syncookie *ctx)
+{
+	struct bpf_sock_tuple tuple;
+	struct bpf_sock *skc;
+	int ret = TC_ACT_OK;
+	struct sock *sk;
+	u32 tuple_size;
+
+	if (ctx->ipv4) {
+		tuple.ipv4.saddr = ctx->ipv4->saddr;
+		tuple.ipv4.daddr = ctx->ipv4->daddr;
+		tuple.ipv4.sport = ctx->tcp->source;
+		tuple.ipv4.dport = ctx->tcp->dest;
+		tuple_size = sizeof(tuple.ipv4);
+	} else if (ctx->ipv6) {
+		__builtin_memcpy(tuple.ipv6.saddr, &ctx->ipv6->saddr, sizeof(tuple.ipv6.saddr));
+		__builtin_memcpy(tuple.ipv6.daddr, &ctx->ipv6->daddr, sizeof(tuple.ipv6.daddr));
+		tuple.ipv6.sport = ctx->tcp->source;
+		tuple.ipv6.dport = ctx->tcp->dest;
+		tuple_size = sizeof(tuple.ipv6);
+	} else {
+		goto out;
+	}
+
+	skc = bpf_skc_lookup_tcp(ctx->skb, &tuple, tuple_size, -1, 0);
+	if (!skc)
+		goto out;
+
+	if (skc->state != TCP_LISTEN)
+		goto release;
+
+	sk = (struct sock *)bpf_skc_to_tcp_sock(skc);
+	if (!sk)
+		goto err;
+
+	if (tcp_validate_header(ctx))
+		goto err;
+
+	tcp_parse_options(ctx);
+
+	if (tcp_validate_cookie(ctx))
+		goto err;
+
+	ret = bpf_sk_assign_tcp_reqsk(ctx->skb, sk, &ctx->attrs, sizeof(ctx->attrs));
+	if (ret < 0)
+		goto err;
+
+release:
+	bpf_sk_release(skc);
+out:
+	return ret;
+
+err:
+	ret = TC_ACT_SHOT;
+	goto release;
+}
+
+SEC("tc")
+int tcp_custom_syncookie(struct __sk_buff *skb)
+{
+	struct tcp_syncookie ctx = {
+		.skb = skb,
+	};
+
+	if (tcp_load_headers(&ctx))
+		return TC_ACT_OK;
+
+	if (ctx.tcp->rst)
+		return TC_ACT_OK;
+
+	if (ctx.tcp->syn) {
+		if (ctx.tcp->ack)
+			return TC_ACT_OK;
+
+		handled_syn = true;
+
+		return tcp_handle_syn(&ctx);
+	}
+
+	handled_ack = true;
+
+	return tcp_handle_ack(&ctx);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.h b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.h
new file mode 100644
index 0000000000..29a6a53cf2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.h
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#ifndef _TEST_TCP_SYNCOOKIE_H
+#define _TEST_TCP_SYNCOOKIE_H
+
+#define __packed __attribute__((__packed__))
+#define __force
+
+#define ARRAY_SIZE(arr)	(sizeof(arr) / sizeof((arr)[0]))
+
+#define swap(a, b)				\
+	do {					\
+		typeof(a) __tmp = (a);		\
+		(a) = (b);			\
+		(b) = __tmp;			\
+	} while (0)
+
+#define swap_array(a, b)				\
+	do {						\
+		typeof(a) __tmp[sizeof(a)];		\
+		__builtin_memcpy(__tmp, a, sizeof(a));	\
+		__builtin_memcpy(a, b, sizeof(a));	\
+		__builtin_memcpy(b, __tmp, sizeof(a));	\
+	} while (0)
+
+/* asm-generic/unaligned.h */
+#define __get_unaligned_t(type, ptr) ({						\
+	const struct { type x; } __packed * __pptr = (typeof(__pptr))(ptr);	\
+	__pptr->x;								\
+})
+
+#define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr))
+
+static inline u16 get_unaligned_be16(const void *p)
+{
+	return bpf_ntohs(__get_unaligned_t(__be16, p));
+}
+
+static inline u32 get_unaligned_be32(const void *p)
+{
+	return bpf_ntohl(__get_unaligned_t(__be32, p));
+}
+
+/* lib/checksum.c */
+static inline u32 from64to32(u64 x)
+{
+	/* add up 32-bit and 32-bit for 32+c bit */
+	x = (x & 0xffffffff) + (x >> 32);
+	/* add up carry.. */
+	x = (x & 0xffffffff) + (x >> 32);
+	return (u32)x;
+}
+
+static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+					__u32 len, __u8 proto, __wsum sum)
+{
+	unsigned long long s = (__force u32)sum;
+
+	s += (__force u32)saddr;
+	s += (__force u32)daddr;
+#ifdef __BIG_ENDIAN
+	s += proto + len;
+#else
+	s += (proto + len) << 8;
+#endif
+	return (__force __wsum)from64to32(s);
+}
+
+/* asm-generic/checksum.h */
+static inline __sum16 csum_fold(__wsum csum)
+{
+	u32 sum = (__force u32)csum;
+
+	sum = (sum & 0xffff) + (sum >> 16);
+	sum = (sum & 0xffff) + (sum >> 16);
+	return (__force __sum16)~sum;
+}
+
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
+					__u8 proto, __wsum sum)
+{
+	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
+}
+
+/* net/ipv6/ip6_checksum.c */
+static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+				      const struct in6_addr *daddr,
+				      __u32 len, __u8 proto, __wsum csum)
+{
+	int carry;
+	__u32 ulen;
+	__u32 uproto;
+	__u32 sum = (__force u32)csum;
+
+	sum += (__force u32)saddr->in6_u.u6_addr32[0];
+	carry = (sum < (__force u32)saddr->in6_u.u6_addr32[0]);
+	sum += carry;
+
+	sum += (__force u32)saddr->in6_u.u6_addr32[1];
+	carry = (sum < (__force u32)saddr->in6_u.u6_addr32[1]);
+	sum += carry;
+
+	sum += (__force u32)saddr->in6_u.u6_addr32[2];
+	carry = (sum < (__force u32)saddr->in6_u.u6_addr32[2]);
+	sum += carry;
+
+	sum += (__force u32)saddr->in6_u.u6_addr32[3];
+	carry = (sum < (__force u32)saddr->in6_u.u6_addr32[3]);
+	sum += carry;
+
+	sum += (__force u32)daddr->in6_u.u6_addr32[0];
+	carry = (sum < (__force u32)daddr->in6_u.u6_addr32[0]);
+	sum += carry;
+
+	sum += (__force u32)daddr->in6_u.u6_addr32[1];
+	carry = (sum < (__force u32)daddr->in6_u.u6_addr32[1]);
+	sum += carry;
+
+	sum += (__force u32)daddr->in6_u.u6_addr32[2];
+	carry = (sum < (__force u32)daddr->in6_u.u6_addr32[2]);
+	sum += carry;
+
+	sum += (__force u32)daddr->in6_u.u6_addr32[3];
+	carry = (sum < (__force u32)daddr->in6_u.u6_addr32[3]);
+	sum += carry;
+
+	ulen = (__force u32)bpf_htonl((__u32)len);
+	sum += ulen;
+	carry = (sum < ulen);
+	sum += carry;
+
+	uproto = (__force u32)bpf_htonl(proto);
+	sum += uproto;
+	carry = (sum < uproto);
+	sum += carry;
+
+	return csum_fold((__force __wsum)sum);
+}
+#endif
diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
index cf7ed8cbb1..a3f3f43fc1 100644
--- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
@@ -59,7 +59,7 @@ int bpf_testcb(struct bpf_sock_ops *skops)
 
 	asm volatile (
 		"%[op] = *(u32 *)(%[skops] +96)"
-		: [op] "+r"(op)
+		: [op] "=r"(op)
 		: [skops] "r"(skops)
 		:);
 
diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c
index d7a9a74b72..8caf58be58 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp.c
@@ -19,6 +19,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 #include "test_iptunnel_common.h"
+#include "bpf_compiler.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
@@ -137,7 +138,7 @@ static __always_inline int handle_ipv4(struct xdp_md *xdp)
 	iph->ttl = 8;
 
 	next_iph = (__u16 *)iph;
-#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (i = 0; i < sizeof(*iph) >> 1; i++)
 		csum += *next_iph++;
 
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c
index 78c368e717..67a77944ef 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c
@@ -18,11 +18,11 @@
 #include "test_iptunnel_common.h"
 #include "bpf_kfuncs.h"
 
-const size_t tcphdr_sz = sizeof(struct tcphdr);
-const size_t udphdr_sz = sizeof(struct udphdr);
-const size_t ethhdr_sz = sizeof(struct ethhdr);
-const size_t iphdr_sz = sizeof(struct iphdr);
-const size_t ipv6hdr_sz = sizeof(struct ipv6hdr);
+#define tcphdr_sz sizeof(struct tcphdr)
+#define udphdr_sz sizeof(struct udphdr)
+#define ethhdr_sz sizeof(struct ethhdr)
+#define iphdr_sz sizeof(struct iphdr)
+#define ipv6hdr_sz sizeof(struct ipv6hdr)
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c
index c98fb44156..93267a6882 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_loop.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c
@@ -15,6 +15,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 #include "test_iptunnel_common.h"
+#include "bpf_compiler.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
@@ -133,7 +134,7 @@ static __always_inline int handle_ipv4(struct xdp_md *xdp)
 	iph->ttl = 8;
 
 	next_iph = (__u16 *)iph;
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 	for (i = 0; i < sizeof(*iph) >> 1; i++)
 		csum += *next_iph++;
 
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
index 42c8f6ded0..5c7e4758a0 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
@@ -15,6 +15,7 @@
 #include <linux/udp.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
+#include "bpf_compiler.h"
 
 static __always_inline __u32 rol32(__u32 word, unsigned int shift)
 {
@@ -362,7 +363,7 @@ bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval,
 	iph->ttl = 4;
 
 	next_iph_u16 = (__u16 *) iph;
-#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (int i = 0; i < sizeof(struct iphdr) >> 1; i++)
 		csum += *next_iph_u16++;
 	iph->check = ~((csum & 0xffff) + (csum >> 16));
@@ -409,7 +410,7 @@ int send_icmp_reply(void *data, void *data_end)
 	iph->saddr = tmp_addr;
 	iph->check = 0;
 	next_iph_u16 = (__u16 *) iph;
-#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (int i = 0; i < sizeof(struct iphdr) >> 1; i++)
 		csum += *next_iph_u16++;
 	iph->check = ~((csum & 0xffff) + (csum >> 16));
diff --git a/tools/testing/selftests/bpf/progs/token_lsm.c b/tools/testing/selftests/bpf/progs/token_lsm.c
new file mode 100644
index 0000000000..e4d59b6ba7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/token_lsm.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+int my_pid;
+bool reject_capable;
+bool reject_cmd;
+
+SEC("lsm/bpf_token_capable")
+int BPF_PROG(token_capable, struct bpf_token *token, int cap)
+{
+	if (my_pid == 0 || my_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+	if (reject_capable)
+		return -1;
+	return 0;
+}
+
+SEC("lsm/bpf_token_cmd")
+int BPF_PROG(token_cmd, struct bpf_token *token, enum bpf_cmd cmd)
+{
+	if (my_pid == 0 || my_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+	if (reject_cmd)
+		return -1;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/tracing_failure.c b/tools/testing/selftests/bpf/progs/tracing_failure.c
new file mode 100644
index 0000000000..d41665d2ec
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tracing_failure.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC("?fentry/bpf_spin_lock")
+int BPF_PROG(test_spin_lock, struct bpf_spin_lock *lock)
+{
+	return 0;
+}
+
+SEC("?fentry/bpf_spin_unlock")
+int BPF_PROG(test_spin_unlock, struct bpf_spin_lock *lock)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c
index 694e7cec18..5fda439010 100644
--- a/tools/testing/selftests/bpf/progs/trigger_bench.c
+++ b/tools/testing/selftests/bpf/progs/trigger_bench.c
@@ -33,6 +33,27 @@ int bench_trigger_kprobe(void *ctx)
 	return 0;
 }
 
+SEC("kretprobe/" SYS_PREFIX "sys_getpgid")
+int bench_trigger_kretprobe(void *ctx)
+{
+	__sync_add_and_fetch(&hits, 1);
+	return 0;
+}
+
+SEC("kprobe.multi/" SYS_PREFIX "sys_getpgid")
+int bench_trigger_kprobe_multi(void *ctx)
+{
+	__sync_add_and_fetch(&hits, 1);
+	return 0;
+}
+
+SEC("kretprobe.multi/" SYS_PREFIX "sys_getpgid")
+int bench_trigger_kretprobe_multi(void *ctx)
+{
+	__sync_add_and_fetch(&hits, 1);
+	return 0;
+}
+
 SEC("fentry/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_fentry(void *ctx)
 {
@@ -40,6 +61,13 @@ int bench_trigger_fentry(void *ctx)
 	return 0;
 }
 
+SEC("fexit/" SYS_PREFIX "sys_getpgid")
+int bench_trigger_fexit(void *ctx)
+{
+	__sync_add_and_fetch(&hits, 1);
+	return 0;
+}
+
 SEC("fentry.s/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_fentry_sleep(void *ctx)
 {
diff --git a/tools/testing/selftests/bpf/progs/type_cast.c b/tools/testing/selftests/bpf/progs/type_cast.c
index a9629ac230..9d808b8f4a 100644
--- a/tools/testing/selftests/bpf/progs/type_cast.c
+++ b/tools/testing/selftests/bpf/progs/type_cast.c
@@ -4,6 +4,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_core_read.h>
+#include "bpf_kfuncs.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
@@ -19,9 +20,6 @@ char name[IFNAMSIZ];
 unsigned int inum;
 unsigned int meta_len, frag0_len, kskb_len, kskb2_len;
 
-void *bpf_cast_to_kern_ctx(void *) __ksym;
-void *bpf_rdonly_cast(void *, __u32) __ksym;
-
 SEC("?xdp")
 int md_xdp(struct xdp_md *ctx)
 {
@@ -48,13 +46,12 @@ int md_skb(struct __sk_buff *skb)
 	/* Simulate the following kernel macro:
 	 *   #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB)))
 	 */
-	shared_info = bpf_rdonly_cast(kskb->head + kskb->end,
-		bpf_core_type_id_kernel(struct skb_shared_info));
+	shared_info = bpf_core_cast(kskb->head + kskb->end, struct skb_shared_info);
 	meta_len = shared_info->meta_len;
 	frag0_len = shared_info->frag_list->len;
 
 	/* kskb2 should be equal to kskb */
-	kskb2 = bpf_rdonly_cast(kskb, bpf_core_type_id_kernel(struct sk_buff));
+	kskb2 = bpf_core_cast(kskb, typeof(*kskb2));
 	kskb2_len = kskb2->len;
 	return 0;
 }
@@ -65,7 +62,7 @@ int BPF_PROG(untrusted_ptr, struct pt_regs *regs, long id)
 	struct task_struct *task, *task_dup;
 
 	task = bpf_get_current_task_btf();
-	task_dup = bpf_rdonly_cast(task, bpf_core_type_id_kernel(struct task_struct));
+	task_dup = bpf_core_cast(task, struct task_struct);
 	(void)bpf_task_storage_get(&enter_id, task_dup, 0, 0);
 	return 0;
 }
@@ -73,7 +70,7 @@ int BPF_PROG(untrusted_ptr, struct pt_regs *regs, long id)
 SEC("?tracepoint/syscalls/sys_enter_nanosleep")
 int kctx_u64(void *ctx)
 {
-	u64 *kctx = bpf_rdonly_cast(ctx, bpf_core_type_id_kernel(u64));
+	u64 *kctx = bpf_core_cast(ctx, u64);
 
 	(void)kctx;
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/verifier_arena.c b/tools/testing/selftests/bpf/progs/verifier_arena.c
new file mode 100644
index 0000000000..93144ae6df
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_arena.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+#include "bpf_arena_common.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, 2); /* arena of two pages close to 32-bit boundary*/
+#ifdef __TARGET_ARCH_arm64
+        __ulong(map_extra, (1ull << 32) | (~0u - __PAGE_SIZE * 2 + 1)); /* start of mmap() region */
+#else
+        __ulong(map_extra, (1ull << 44) | (~0u - __PAGE_SIZE * 2 + 1)); /* start of mmap() region */
+#endif
+} arena SEC(".maps");
+
+SEC("syscall")
+__success __retval(0)
+int basic_alloc1(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	volatile int __arena *page1, *page2, *no_page, *page3;
+
+	page1 = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (!page1)
+		return 1;
+	*page1 = 1;
+	page2 = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (!page2)
+		return 2;
+	*page2 = 2;
+	no_page = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (no_page)
+		return 3;
+	if (*page1 != 1)
+		return 4;
+	if (*page2 != 2)
+		return 5;
+	bpf_arena_free_pages(&arena, (void __arena *)page2, 1);
+	if (*page1 != 1)
+		return 6;
+	if (*page2 != 0) /* use-after-free should return 0 */
+		return 7;
+	page3 = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (!page3)
+		return 8;
+	*page3 = 3;
+	if (page2 != page3)
+		return 9;
+	if (*page1 != 1)
+		return 10;
+#endif
+	return 0;
+}
+
+SEC("syscall")
+__success __retval(0)
+int basic_alloc2(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	volatile char __arena *page1, *page2, *page3, *page4;
+
+	page1 = bpf_arena_alloc_pages(&arena, NULL, 2, NUMA_NO_NODE, 0);
+	if (!page1)
+		return 1;
+	page2 = page1 + __PAGE_SIZE;
+	page3 = page1 + __PAGE_SIZE * 2;
+	page4 = page1 - __PAGE_SIZE;
+	*page1 = 1;
+	*page2 = 2;
+	*page3 = 3;
+	*page4 = 4;
+	if (*page1 != 1)
+		return 1;
+	if (*page2 != 2)
+		return 2;
+	if (*page3 != 0)
+		return 3;
+	if (*page4 != 0)
+		return 4;
+	bpf_arena_free_pages(&arena, (void __arena *)page1, 2);
+	if (*page1 != 0)
+		return 5;
+	if (*page2 != 0)
+		return 6;
+	if (*page3 != 0)
+		return 7;
+	if (*page4 != 0)
+		return 8;
+#endif
+	return 0;
+}
+
+struct bpf_arena___l {
+        struct bpf_map map;
+} __attribute__((preserve_access_index));
+
+SEC("syscall")
+__success __retval(0) __log_level(2)
+int basic_alloc3(void *ctx)
+{
+	struct bpf_arena___l *ar = (struct bpf_arena___l *)&arena;
+	volatile char __arena *pages;
+
+	pages = bpf_arena_alloc_pages(&ar->map, NULL, ar->map.max_entries, NUMA_NO_NODE, 0);
+	if (!pages)
+		return 1;
+	return 0;
+}
+
+SEC("iter.s/bpf_map")
+__success __log_level(2)
+int iter_maps1(struct bpf_iter__bpf_map *ctx)
+{
+	struct bpf_map *map = ctx->map;
+
+	if (!map)
+		return 0;
+	bpf_arena_alloc_pages(map, NULL, map->max_entries, 0, 0);
+	return 0;
+}
+
+SEC("iter.s/bpf_map")
+__failure __msg("expected pointer to STRUCT bpf_map")
+int iter_maps2(struct bpf_iter__bpf_map *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+
+	bpf_arena_alloc_pages((void *)seq, NULL, 1, 0, 0);
+	return 0;
+}
+
+SEC("iter.s/bpf_map")
+__failure __msg("untrusted_ptr_bpf_map")
+int iter_maps3(struct bpf_iter__bpf_map *ctx)
+{
+	struct bpf_map *map = ctx->map;
+
+	if (!map)
+		return 0;
+	bpf_arena_alloc_pages(map->inner_map_meta, NULL, map->max_entries, 0, 0);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_arena_large.c b/tools/testing/selftests/bpf/progs/verifier_arena_large.c
new file mode 100644
index 0000000000..ef66ea4602
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_arena_large.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+#include "bpf_arena_common.h"
+
+#define ARENA_SIZE (1ull << 32)
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, ARENA_SIZE / PAGE_SIZE);
+} arena SEC(".maps");
+
+SEC("syscall")
+__success __retval(0)
+int big_alloc1(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	volatile char __arena *page1, *page2, *no_page, *page3;
+	void __arena *base;
+
+	page1 = base = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (!page1)
+		return 1;
+	*page1 = 1;
+	page2 = bpf_arena_alloc_pages(&arena, base + ARENA_SIZE - PAGE_SIZE,
+				      1, NUMA_NO_NODE, 0);
+	if (!page2)
+		return 2;
+	*page2 = 2;
+	no_page = bpf_arena_alloc_pages(&arena, base + ARENA_SIZE,
+					1, NUMA_NO_NODE, 0);
+	if (no_page)
+		return 3;
+	if (*page1 != 1)
+		return 4;
+	if (*page2 != 2)
+		return 5;
+	bpf_arena_free_pages(&arena, (void __arena *)page1, 1);
+	if (*page2 != 2)
+		return 6;
+	if (*page1 != 0) /* use-after-free should return 0 */
+		return 7;
+	page3 = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (!page3)
+		return 8;
+	*page3 = 3;
+	if (page1 != page3)
+		return 9;
+	if (*page2 != 2)
+		return 10;
+	if (*(page1 + PAGE_SIZE) != 0)
+		return 11;
+	if (*(page1 - PAGE_SIZE) != 0)
+		return 12;
+	if (*(page2 + PAGE_SIZE) != 0)
+		return 13;
+	if (*(page2 - PAGE_SIZE) != 0)
+		return 14;
+#endif
+	return 0;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c b/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c
index be95570ab3..28b602ac9c 100644
--- a/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c
+++ b/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c
@@ -568,7 +568,7 @@ l0_%=:	r0 = 0;						\
 
 SEC("tc")
 __description("direct packet access: test23 (x += pkt_ptr, 4)")
-__failure __msg("invalid access to packet, off=0 size=8, R5(id=2,off=0,r=0)")
+__failure __msg("invalid access to packet, off=0 size=8, R5(id=3,off=0,r=0)")
 __flag(BPF_F_ANY_ALIGNMENT)
 __naked void test23_x_pkt_ptr_4(void)
 {
diff --git a/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c b/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c
new file mode 100644
index 0000000000..4ab0ef18d7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c
@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
+#include "xdp_metadata.h"
+#include "bpf_kfuncs.h"
+
+extern struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym __weak;
+extern void bpf_task_release(struct task_struct *p) __ksym __weak;
+
+__weak int subprog_trusted_task_nullable(struct task_struct *task __arg_trusted __arg_nullable)
+{
+	if (!task)
+		return 0;
+	return task->pid + task->tgid;
+}
+
+__weak int subprog_trusted_task_nullable_extra_layer(struct task_struct *task __arg_trusted __arg_nullable)
+{
+	return subprog_trusted_task_nullable(task) + subprog_trusted_task_nullable(NULL);
+}
+
+SEC("?tp_btf/task_newtask")
+__success __log_level(2)
+__msg("Validating subprog_trusted_task_nullable() func#1...")
+__msg(": R1=trusted_ptr_or_null_task_struct(")
+int trusted_task_arg_nullable(void *ctx)
+{
+	struct task_struct *t1 = bpf_get_current_task_btf();
+	struct task_struct *t2 = bpf_task_acquire(t1);
+	int res = 0;
+
+	/* known NULL */
+	res += subprog_trusted_task_nullable(NULL);
+
+	/* known non-NULL */
+	res += subprog_trusted_task_nullable(t1);
+	res += subprog_trusted_task_nullable_extra_layer(t1);
+
+	/* unknown if NULL or not */
+	res += subprog_trusted_task_nullable(t2);
+	res += subprog_trusted_task_nullable_extra_layer(t2);
+
+	if (t2) {
+		/* known non-NULL after explicit NULL check, just in case */
+		res += subprog_trusted_task_nullable(t2);
+		res += subprog_trusted_task_nullable_extra_layer(t2);
+
+		bpf_task_release(t2);
+	}
+
+	return res;
+}
+
+__weak int subprog_trusted_task_nonnull(struct task_struct *task __arg_trusted)
+{
+	return task->pid + task->tgid;
+}
+
+SEC("?kprobe")
+__failure __log_level(2)
+__msg("R1 type=scalar expected=ptr_, trusted_ptr_, rcu_ptr_")
+__msg("Caller passes invalid args into func#1 ('subprog_trusted_task_nonnull')")
+int trusted_task_arg_nonnull_fail1(void *ctx)
+{
+	return subprog_trusted_task_nonnull(NULL);
+}
+
+SEC("?tp_btf/task_newtask")
+__failure __log_level(2)
+__msg("R1 type=ptr_or_null_ expected=ptr_, trusted_ptr_, rcu_ptr_")
+__msg("Caller passes invalid args into func#1 ('subprog_trusted_task_nonnull')")
+int trusted_task_arg_nonnull_fail2(void *ctx)
+{
+	struct task_struct *t = bpf_get_current_task_btf();
+	struct task_struct *nullable;
+	int res;
+
+	nullable = bpf_task_acquire(t);
+
+	 /* should fail, PTR_TO_BTF_ID_OR_NULL */
+	res = subprog_trusted_task_nonnull(nullable);
+
+	if (nullable)
+		bpf_task_release(nullable);
+
+	return res;
+}
+
+SEC("?kprobe")
+__success __log_level(2)
+__msg("Validating subprog_trusted_task_nonnull() func#1...")
+__msg(": R1=trusted_ptr_task_struct(")
+int trusted_task_arg_nonnull(void *ctx)
+{
+	struct task_struct *t = bpf_get_current_task_btf();
+
+	return subprog_trusted_task_nonnull(t);
+}
+
+struct task_struct___local {} __attribute__((preserve_access_index));
+
+__weak int subprog_nullable_task_flavor(
+	struct task_struct___local *task __arg_trusted __arg_nullable)
+{
+	char buf[16];
+
+	if (!task)
+		return 0;
+
+	return bpf_copy_from_user_task(&buf, sizeof(buf), NULL, (void *)task, 0);
+}
+
+SEC("?uprobe.s")
+__success __log_level(2)
+__msg("Validating subprog_nullable_task_flavor() func#1...")
+__msg(": R1=trusted_ptr_or_null_task_struct(")
+int flavor_ptr_nullable(void *ctx)
+{
+	struct task_struct___local *t = (void *)bpf_get_current_task_btf();
+
+	return subprog_nullable_task_flavor(t);
+}
+
+__weak int subprog_nonnull_task_flavor(struct task_struct___local *task __arg_trusted)
+{
+	char buf[16];
+
+	return bpf_copy_from_user_task(&buf, sizeof(buf), NULL, (void *)task, 0);
+}
+
+SEC("?uprobe.s")
+__success __log_level(2)
+__msg("Validating subprog_nonnull_task_flavor() func#1...")
+__msg(": R1=trusted_ptr_task_struct(")
+int flavor_ptr_nonnull(void *ctx)
+{
+	struct task_struct *t = bpf_get_current_task_btf();
+
+	return subprog_nonnull_task_flavor((void *)t);
+}
+
+__weak int subprog_trusted_destroy(struct task_struct *task __arg_trusted)
+{
+	bpf_task_release(task); /* should be rejected */
+
+	return 0;
+}
+
+SEC("?tp_btf/task_newtask")
+__failure __log_level(2)
+__msg("release kernel function bpf_task_release expects refcounted PTR_TO_BTF_ID")
+int BPF_PROG(trusted_destroy_fail, struct task_struct *task, u64 clone_flags)
+{
+	return subprog_trusted_destroy(task);
+}
+
+__weak int subprog_trusted_acq_rel(struct task_struct *task __arg_trusted)
+{
+	struct task_struct *owned;
+
+	owned = bpf_task_acquire(task);
+	if (!owned)
+		return 0;
+
+	bpf_task_release(owned); /* this one is OK, we acquired it locally */
+
+	return 0;
+}
+
+SEC("?tp_btf/task_newtask")
+__success __log_level(2)
+int BPF_PROG(trusted_acq_rel, struct task_struct *task, u64 clone_flags)
+{
+	return subprog_trusted_acq_rel(task);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
index 67dddd9418..baff5ffe94 100644
--- a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
+++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
@@ -115,6 +115,35 @@ int arg_tag_nullable_ptr_fail(void *ctx)
 	return subprog_nullable_ptr_bad(&x);
 }
 
+typedef struct {
+	int x;
+} user_struct_t;
+
+__noinline __weak int subprog_user_anon_mem(user_struct_t *t)
+{
+	return t ? t->x : 0;
+}
+
+SEC("?tracepoint")
+__failure __log_level(2)
+__msg("invalid bpf_context access")
+__msg("Caller passes invalid args into func#1 ('subprog_user_anon_mem')")
+int anon_user_mem_invalid(void *ctx)
+{
+	/* can't pass PTR_TO_CTX as user memory */
+	return subprog_user_anon_mem(ctx);
+}
+
+SEC("?tracepoint")
+__success __log_level(2)
+__msg("Func#1 ('subprog_user_anon_mem') is safe for any args that match its prototype")
+int anon_user_mem_valid(void *ctx)
+{
+	user_struct_t t = { .x = 42 };
+
+	return subprog_user_anon_mem(&t);
+}
+
 __noinline __weak int subprog_nonnull_ptr_good(int *p1 __arg_nonnull, int *p2 __arg_nonnull)
 {
 	return (*p1) * (*p2); /* good, no need for NULL checks */
diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
index a955a63582..99e561f18f 100644
--- a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
+++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
@@ -1,8 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
-
-#include <linux/bpf.h>
-#include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
+#include "bpf_experimental.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
@@ -309,4 +307,103 @@ int iter_limit_bug(struct __sk_buff *skb)
 	return 0;
 }
 
+#define ARR_SZ 1000000
+int zero;
+char arr[ARR_SZ];
+
+SEC("socket")
+__success __retval(0xd495cdc0)
+int cond_break1(const void *ctx)
+{
+	unsigned long i;
+	unsigned int sum = 0;
+
+	for (i = zero; i < ARR_SZ; cond_break, i++)
+		sum += i;
+	for (i = zero; i < ARR_SZ; i++) {
+		barrier_var(i);
+		sum += i + arr[i];
+		cond_break;
+	}
+
+	return sum;
+}
+
+SEC("socket")
+__success __retval(999000000)
+int cond_break2(const void *ctx)
+{
+	int i, j;
+	int sum = 0;
+
+	for (i = zero; i < 1000; cond_break, i++)
+		for (j = zero; j < 1000; j++) {
+			sum += i + j;
+			cond_break;
+		}
+
+	return sum;
+}
+
+static __noinline int loop(void)
+{
+	int i, sum = 0;
+
+	for (i = zero; i <= 1000000; i++, cond_break)
+		sum += i;
+
+	return sum;
+}
+
+SEC("socket")
+__success __retval(0x6a5a2920)
+int cond_break3(const void *ctx)
+{
+	return loop();
+}
+
+SEC("socket")
+__success __retval(1)
+int cond_break4(const void *ctx)
+{
+	int cnt = zero;
+
+	for (;;) {
+		/* should eventually break out of the loop */
+		cond_break;
+		cnt++;
+	}
+	/* if we looped a bit, it's a success */
+	return cnt > 1 ? 1 : 0;
+}
+
+static __noinline int static_subprog(void)
+{
+	int cnt = zero;
+
+	for (;;) {
+		cond_break;
+		cnt++;
+	}
+
+	return cnt;
+}
+
+SEC("socket")
+__success __retval(1)
+int cond_break5(const void *ctx)
+{
+	int cnt1 = zero, cnt2;
+
+	for (;;) {
+		cond_break;
+		cnt1++;
+	}
+
+	cnt2 = static_subprog();
+
+	/* main and subprog have to loop a bit */
+	return cnt1 > 1 && cnt2 > 1 ? 1 : 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_loops1.c b/tools/testing/selftests/bpf/progs/verifier_loops1.c
index 71735dbf33..e07b43b78f 100644
--- a/tools/testing/selftests/bpf/progs/verifier_loops1.c
+++ b/tools/testing/selftests/bpf/progs/verifier_loops1.c
@@ -259,4 +259,28 @@ l0_%=:	r2 += r1;					\
 "	::: __clobber_all);
 }
 
+SEC("xdp")
+__success
+__naked void not_an_inifinite_loop(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0xff;					\
+	*(u64 *)(r10 - 8) = r0;				\
+	r0 = 0;						\
+loop_%=:						\
+	r0 = *(u64 *)(r10 - 8);				\
+	if r0 > 10 goto exit_%=;			\
+	r0 += 1;					\
+	*(u64 *)(r10 - 8) = r0;				\
+	r0 = 0;						\
+	goto loop_%=;					\
+exit_%=:						\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
index 39fe3372e0..85e48069c9 100644
--- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
+++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
@@ -217,7 +217,7 @@ __naked void uninit_u32_from_the_stack(void)
 
 SEC("tc")
 __description("Spill a u32 const scalar.  Refill as u16.  Offset to skb->data")
-__failure __msg("invalid access to packet")
+__success __retval(0)
 __naked void u16_offset_to_skb_data(void)
 {
 	asm volatile ("					\
@@ -225,13 +225,19 @@ __naked void u16_offset_to_skb_data(void)
 	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
 	w4 = 20;					\
 	*(u32*)(r10 - 8) = r4;				\
-	r4 = *(u16*)(r10 - 8);				\
+	"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r4 = *(u16*)(r10 - 8);"
+#else
+	"r4 = *(u16*)(r10 - 6);"
+#endif
+	"						\
 	r0 = r2;					\
-	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */\
+	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=20 */\
 	r0 += r4;					\
-	/* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=umax=65535 */\
+	/* if (r0 > r3) R0=pkt,off=20 R2=pkt R3=pkt_end R4=20 */\
 	if r0 > r3 goto l0_%=;				\
-	/* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=20 */\
+	/* r0 = *(u32 *)r2 R0=pkt,off=20 R2=pkt R3=pkt_end R4=20 */\
 	r0 = *(u32*)(r2 + 0);				\
 l0_%=:	r0 = 0;						\
 	exit;						\
@@ -243,7 +249,7 @@ l0_%=:	r0 = 0;						\
 
 SEC("tc")
 __description("Spill u32 const scalars.  Refill as u64.  Offset to skb->data")
-__failure __msg("invalid access to packet")
+__failure __msg("math between pkt pointer and register with unbounded min value is not allowed")
 __naked void u64_offset_to_skb_data(void)
 {
 	asm volatile ("					\
@@ -253,13 +259,11 @@ __naked void u64_offset_to_skb_data(void)
 	w7 = 20;					\
 	*(u32*)(r10 - 4) = r6;				\
 	*(u32*)(r10 - 8) = r7;				\
-	r4 = *(u16*)(r10 - 8);				\
+	r4 = *(u64*)(r10 - 8);				\
 	r0 = r2;					\
-	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */\
+	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4= */	\
 	r0 += r4;					\
-	/* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=umax=65535 */\
 	if r0 > r3 goto l0_%=;				\
-	/* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=20 */\
 	r0 = *(u32*)(r2 + 0);				\
 l0_%=:	r0 = 0;						\
 	exit;						\
@@ -270,7 +274,7 @@ l0_%=:	r0 = 0;						\
 }
 
 SEC("tc")
-__description("Spill a u32 const scalar.  Refill as u16 from fp-6.  Offset to skb->data")
+__description("Spill a u32 const scalar.  Refill as u16 from MSB.  Offset to skb->data")
 __failure __msg("invalid access to packet")
 __naked void _6_offset_to_skb_data(void)
 {
@@ -279,7 +283,13 @@ __naked void _6_offset_to_skb_data(void)
 	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
 	w4 = 20;					\
 	*(u32*)(r10 - 8) = r4;				\
-	r4 = *(u16*)(r10 - 6);				\
+	"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r4 = *(u16*)(r10 - 6);"
+#else
+	"r4 = *(u16*)(r10 - 8);"
+#endif
+	"						\
 	r0 = r2;					\
 	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */\
 	r0 += r4;					\
@@ -454,9 +464,9 @@ l0_%=:	r1 >>= 16;					\
 SEC("raw_tp")
 __log_level(2)
 __success
-__msg("fp-8=0m??mmmm")
-__msg("fp-16=00mm??mm")
-__msg("fp-24=00mm???m")
+__msg("fp-8=0m??scalar()")
+__msg("fp-16=00mm??scalar()")
+__msg("fp-24=00mm???scalar()")
 __naked void spill_subregs_preserve_stack_zero(void)
 {
 	asm volatile (
@@ -495,14 +505,14 @@ char single_byte_buf[1] SEC(".data.single_byte_buf");
 SEC("raw_tp")
 __log_level(2)
 __success
-/* make sure fp-8 is all STACK_ZERO */
-__msg("2: (7a) *(u64 *)(r10 -8) = 0          ; R10=fp0 fp-8_w=00000000")
+/* fp-8 is spilled IMPRECISE value zero (represented by a zero value fake reg) */
+__msg("2: (7a) *(u64 *)(r10 -8) = 0          ; R10=fp0 fp-8_w=0")
 /* but fp-16 is spilled IMPRECISE zero const reg */
 __msg("4: (7b) *(u64 *)(r10 -16) = r0        ; R0_w=0 R10=fp0 fp-16_w=0")
-/* validate that assigning R2 from STACK_ZERO doesn't mark register
+/* validate that assigning R2 from STACK_SPILL with zero value  doesn't mark register
  * precise immediately; if necessary, it will be marked precise later
  */
-__msg("6: (71) r2 = *(u8 *)(r10 -1)          ; R2_w=0 R10=fp0 fp-8_w=00000000")
+__msg("6: (71) r2 = *(u8 *)(r10 -1)          ; R2_w=0 R10=fp0 fp-8_w=0")
 /* similarly, when R2 is assigned from spilled register, it is initially
  * imprecise, but will be marked precise later once it is used in precise context
  */
@@ -520,14 +530,14 @@ __msg("mark_precise: frame0: regs=r0 stack= before 3: (b7) r0 = 0")
 __naked void partial_stack_load_preserves_zeros(void)
 {
 	asm volatile (
-		/* fp-8 is all STACK_ZERO */
+		/* fp-8 is value zero (represented by a zero value fake reg) */
 		".8byte %[fp8_st_zero];" /* LLVM-18+: *(u64 *)(r10 -8) = 0; */
 
 		/* fp-16 is const zero register */
 		"r0 = 0;"
 		"*(u64 *)(r10 -16) = r0;"
 
-		/* load single U8 from non-aligned STACK_ZERO slot */
+		/* load single U8 from non-aligned spilled value zero slot */
 		"r1 = %[single_byte_buf];"
 		"r2 = *(u8 *)(r10 -1);"
 		"r1 += r2;"
@@ -539,7 +549,7 @@ __naked void partial_stack_load_preserves_zeros(void)
 		"r1 += r2;"
 		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
 
-		/* load single U16 from non-aligned STACK_ZERO slot */
+		/* load single U16 from non-aligned spilled value zero slot */
 		"r1 = %[single_byte_buf];"
 		"r2 = *(u16 *)(r10 -2);"
 		"r1 += r2;"
@@ -551,7 +561,7 @@ __naked void partial_stack_load_preserves_zeros(void)
 		"r1 += r2;"
 		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
 
-		/* load single U32 from non-aligned STACK_ZERO slot */
+		/* load single U32 from non-aligned spilled value zero slot */
 		"r1 = %[single_byte_buf];"
 		"r2 = *(u32 *)(r10 -4);"
 		"r1 += r2;"
@@ -583,6 +593,47 @@ __naked void partial_stack_load_preserves_zeros(void)
 	: __clobber_common);
 }
 
+SEC("raw_tp")
+__log_level(2)
+__success
+/* fp-4 is STACK_ZERO */
+__msg("2: (62) *(u32 *)(r10 -4) = 0          ; R10=fp0 fp-8=0000????")
+__msg("4: (71) r2 = *(u8 *)(r10 -1)          ; R2_w=0 R10=fp0 fp-8=0000????")
+__msg("5: (0f) r1 += r2")
+__msg("mark_precise: frame0: last_idx 5 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 4: (71) r2 = *(u8 *)(r10 -1)")
+__naked void partial_stack_load_preserves_partial_zeros(void)
+{
+	asm volatile (
+		/* fp-4 is value zero */
+		".8byte %[fp4_st_zero];" /* LLVM-18+: *(u32 *)(r10 -4) = 0; */
+
+		/* load single U8 from non-aligned stack zero slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u8 *)(r10 -1);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U16 from non-aligned stack zero slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u16 *)(r10 -2);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U32 from non-aligned stack zero slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u32 *)(r10 -4);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		"r0 = 0;"
+		"exit;"
+	:
+	: __imm_ptr(single_byte_buf),
+	  __imm_insn(fp4_st_zero, BPF_ST_MEM(BPF_W, BPF_REG_FP, -4, 0))
+	: __clobber_common);
+}
+
 char two_byte_buf[2] SEC(".data.two_byte_buf");
 
 SEC("raw_tp")
@@ -737,4 +788,460 @@ __naked void stack_load_preserves_const_precision_subreg(void)
 	: __clobber_common);
 }
 
+SEC("xdp")
+__description("32-bit spilled reg range should be tracked")
+__success __retval(0)
+__naked void spill_32bit_range_track(void)
+{
+	asm volatile("					\
+	call %[bpf_ktime_get_ns];			\
+	/* Make r0 bounded. */				\
+	r0 &= 65535;					\
+	/* Assign an ID to r0. */			\
+	r1 = r0;					\
+	/* 32-bit spill r0 to stack. */			\
+	*(u32*)(r10 - 8) = r0;				\
+	/* Boundary check on r0. */			\
+	if r0 < 1 goto l0_%=;				\
+	/* 32-bit fill r1 from stack. */		\
+	r1 = *(u32*)(r10 - 8);				\
+	/* r1 == r0 => r1 >= 1 always. */		\
+	if r1 >= 1 goto l0_%=;				\
+	/* Dead branch: the verifier should prune it.   \
+	 * Do an invalid memory access if the verifier	\
+	 * follows it.					\
+	 */						\
+	r0 = *(u64*)(r9 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("64-bit spill of 64-bit reg should assign ID")
+__success __retval(0)
+__naked void spill_64bit_of_64bit_ok(void)
+{
+	asm volatile ("					\
+	/* Roll one bit to make the register inexact. */\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0x80000000;				\
+	r0 <<= 32;					\
+	/* 64-bit spill r0 to stack - should assign an ID. */\
+	*(u64*)(r10 - 8) = r0;				\
+	/* 64-bit fill r1 from stack - should preserve the ID. */\
+	r1 = *(u64*)(r10 - 8);				\
+	/* Compare r1 with another register to trigger find_equal_scalars.\
+	 * Having one random bit is important here, otherwise the verifier cuts\
+	 * the corners.					\
+	 */						\
+	r2 = 0;						\
+	if r1 != r2 goto l0_%=;				\
+	/* The result of this comparison is predefined. */\
+	if r0 == r2 goto l0_%=;				\
+	/* Dead branch: the verifier should prune it. Do an invalid memory\
+	 * access if the verifier follows it.		\
+	 */						\
+	r0 = *(u64*)(r9 + 0);				\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("32-bit spill of 32-bit reg should assign ID")
+__success __retval(0)
+__naked void spill_32bit_of_32bit_ok(void)
+{
+	asm volatile ("					\
+	/* Roll one bit to make the register inexact. */\
+	call %[bpf_get_prandom_u32];			\
+	w0 &= 0x80000000;				\
+	/* 32-bit spill r0 to stack - should assign an ID. */\
+	*(u32*)(r10 - 8) = r0;				\
+	/* 32-bit fill r1 from stack - should preserve the ID. */\
+	r1 = *(u32*)(r10 - 8);				\
+	/* Compare r1 with another register to trigger find_equal_scalars.\
+	 * Having one random bit is important here, otherwise the verifier cuts\
+	 * the corners.					\
+	 */						\
+	r2 = 0;						\
+	if r1 != r2 goto l0_%=;				\
+	/* The result of this comparison is predefined. */\
+	if r0 == r2 goto l0_%=;				\
+	/* Dead branch: the verifier should prune it. Do an invalid memory\
+	 * access if the verifier follows it.		\
+	 */						\
+	r0 = *(u64*)(r9 + 0);				\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("16-bit spill of 16-bit reg should assign ID")
+__success __retval(0)
+__naked void spill_16bit_of_16bit_ok(void)
+{
+	asm volatile ("					\
+	/* Roll one bit to make the register inexact. */\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0x8000;					\
+	/* 16-bit spill r0 to stack - should assign an ID. */\
+	*(u16*)(r10 - 8) = r0;				\
+	/* 16-bit fill r1 from stack - should preserve the ID. */\
+	r1 = *(u16*)(r10 - 8);				\
+	/* Compare r1 with another register to trigger find_equal_scalars.\
+	 * Having one random bit is important here, otherwise the verifier cuts\
+	 * the corners.					\
+	 */						\
+	r2 = 0;						\
+	if r1 != r2 goto l0_%=;				\
+	/* The result of this comparison is predefined. */\
+	if r0 == r2 goto l0_%=;				\
+	/* Dead branch: the verifier should prune it. Do an invalid memory\
+	 * access if the verifier follows it.		\
+	 */						\
+	r0 = *(u64*)(r9 + 0);				\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("8-bit spill of 8-bit reg should assign ID")
+__success __retval(0)
+__naked void spill_8bit_of_8bit_ok(void)
+{
+	asm volatile ("					\
+	/* Roll one bit to make the register inexact. */\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0x80;					\
+	/* 8-bit spill r0 to stack - should assign an ID. */\
+	*(u8*)(r10 - 8) = r0;				\
+	/* 8-bit fill r1 from stack - should preserve the ID. */\
+	r1 = *(u8*)(r10 - 8);				\
+	/* Compare r1 with another register to trigger find_equal_scalars.\
+	 * Having one random bit is important here, otherwise the verifier cuts\
+	 * the corners.					\
+	 */						\
+	r2 = 0;						\
+	if r1 != r2 goto l0_%=;				\
+	/* The result of this comparison is predefined. */\
+	if r0 == r2 goto l0_%=;				\
+	/* Dead branch: the verifier should prune it. Do an invalid memory\
+	 * access if the verifier follows it.		\
+	 */						\
+	r0 = *(u64*)(r9 + 0);				\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("spill unbounded reg, then range check src")
+__success __retval(0)
+__naked void spill_unbounded(void)
+{
+	asm volatile ("					\
+	/* Produce an unbounded scalar. */		\
+	call %[bpf_get_prandom_u32];			\
+	/* Spill r0 to stack. */			\
+	*(u64*)(r10 - 8) = r0;				\
+	/* Boundary check on r0. */			\
+	if r0 > 16 goto l0_%=;				\
+	/* Fill r0 from stack. */			\
+	r0 = *(u64*)(r10 - 8);				\
+	/* Boundary check on r0 with predetermined result. */\
+	if r0 <= 16 goto l0_%=;				\
+	/* Dead branch: the verifier should prune it. Do an invalid memory\
+	 * access if the verifier follows it.		\
+	 */						\
+	r0 = *(u64*)(r9 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("32-bit fill after 64-bit spill")
+__success __retval(0)
+__naked void fill_32bit_after_spill_64bit(void)
+{
+	asm volatile("					\
+	/* Randomize the upper 32 bits. */		\
+	call %[bpf_get_prandom_u32];			\
+	r0 <<= 32;					\
+	/* 64-bit spill r0 to stack. */			\
+	*(u64*)(r10 - 8) = r0;				\
+	/* 32-bit fill r0 from stack. */		\
+	"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(u32*)(r10 - 8);"
+#else
+	"r0 = *(u32*)(r10 - 4);"
+#endif
+	"						\
+	/* Boundary check on r0 with predetermined result. */\
+	if r0 == 0 goto l0_%=;				\
+	/* Dead branch: the verifier should prune it. Do an invalid memory\
+	 * access if the verifier follows it.		\
+	 */						\
+	r0 = *(u64*)(r9 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("32-bit fill after 64-bit spill of 32-bit value should preserve ID")
+__success __retval(0)
+__naked void fill_32bit_after_spill_64bit_preserve_id(void)
+{
+	asm volatile ("					\
+	/* Randomize the lower 32 bits. */		\
+	call %[bpf_get_prandom_u32];			\
+	w0 &= 0xffffffff;				\
+	/* 64-bit spill r0 to stack - should assign an ID. */\
+	*(u64*)(r10 - 8) = r0;				\
+	/* 32-bit fill r1 from stack - should preserve the ID. */\
+	"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r1 = *(u32*)(r10 - 8);"
+#else
+	"r1 = *(u32*)(r10 - 4);"
+#endif
+	"						\
+	/* Compare r1 with another register to trigger find_equal_scalars. */\
+	r2 = 0;						\
+	if r1 != r2 goto l0_%=;				\
+	/* The result of this comparison is predefined. */\
+	if r0 == r2 goto l0_%=;				\
+	/* Dead branch: the verifier should prune it. Do an invalid memory\
+	 * access if the verifier follows it.		\
+	 */						\
+	r0 = *(u64*)(r9 + 0);				\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("32-bit fill after 64-bit spill should clear ID")
+__failure __msg("math between ctx pointer and 4294967295 is not allowed")
+__naked void fill_32bit_after_spill_64bit_clear_id(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	/* Roll one bit to force the verifier to track both branches. */\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0x8;					\
+	/* Put a large number into r1. */		\
+	r1 = 0xffffffff;				\
+	r1 <<= 32;					\
+	r1 += r0;					\
+	/* 64-bit spill r1 to stack - should assign an ID. */\
+	*(u64*)(r10 - 8) = r1;				\
+	/* 32-bit fill r2 from stack - should clear the ID. */\
+	"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r2 = *(u32*)(r10 - 8);"
+#else
+	"r2 = *(u32*)(r10 - 4);"
+#endif
+	"						\
+	/* Compare r2 with another register to trigger find_equal_scalars.\
+	 * Having one random bit is important here, otherwise the verifier cuts\
+	 * the corners. If the ID was mistakenly preserved on fill, this would\
+	 * cause the verifier to think that r1 is also equal to zero in one of\
+	 * the branches, and equal to eight on the other branch.\
+	 */						\
+	r3 = 0;						\
+	if r2 != r3 goto l0_%=;				\
+l0_%=:	r1 >>= 32;					\
+	/* The verifier shouldn't propagate r2's range to r1, so it should\
+	 * still remember r1 = 0xffffffff and reject the below.\
+	 */						\
+	r6 += r1;					\
+	r0 = *(u32*)(r6 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* stacksafe(): check if stack spill of an imprecise scalar in old state
+ * is considered equivalent to STACK_{MISC,INVALID} in cur state.
+ */
+SEC("socket")
+__success __log_level(2)
+__msg("8: (79) r1 = *(u64 *)(r10 -8)")
+__msg("8: safe")
+__msg("processed 11 insns")
+/* STACK_INVALID should prevent verifier in unpriv mode from
+ * considering states equivalent and force an error on second
+ * verification path (entry - label 1 - label 2).
+ */
+__failure_unpriv
+__msg_unpriv("8: (79) r1 = *(u64 *)(r10 -8)")
+__msg_unpriv("9: (95) exit")
+__msg_unpriv("8: (79) r1 = *(u64 *)(r10 -8)")
+__msg_unpriv("invalid read from stack off -8+2 size 8")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void old_imprecise_scalar_vs_cur_stack_misc(void)
+{
+	asm volatile(
+	/* get a random value for branching */
+	"call %[bpf_ktime_get_ns];"
+	"if r0 == 0 goto 1f;"
+	/* conjure scalar at fp-8 */
+	"r0 = 42;"
+	"*(u64*)(r10 - 8) = r0;"
+	"goto 2f;"
+"1:"
+	/* conjure STACK_{MISC,INVALID} at fp-8 */
+	"call %[bpf_ktime_get_ns];"
+	"*(u16*)(r10 - 8) = r0;"
+	"*(u16*)(r10 - 4) = r0;"
+"2:"
+	/* read fp-8, should be considered safe on second visit */
+	"r1 = *(u64*)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* stacksafe(): check that stack spill of a precise scalar in old state
+ * is not considered equivalent to STACK_MISC in cur state.
+ */
+SEC("socket")
+__success __log_level(2)
+/* verifier should visit 'if r1 == 0x2a ...' two times:
+ * - once for path entry - label 2;
+ * - once for path entry - label 1 - label 2.
+ */
+__msg("if r1 == 0x2a goto pc+0")
+__msg("if r1 == 0x2a goto pc+0")
+__msg("processed 15 insns")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void old_precise_scalar_vs_cur_stack_misc(void)
+{
+	asm volatile(
+	/* get a random value for branching */
+	"call %[bpf_ktime_get_ns];"
+	"if r0 == 0 goto 1f;"
+	/* conjure scalar at fp-8 */
+	"r0 = 42;"
+	"*(u64*)(r10 - 8) = r0;"
+	"goto 2f;"
+"1:"
+	/* conjure STACK_MISC at fp-8 */
+	"call %[bpf_ktime_get_ns];"
+	"*(u64*)(r10 - 8) = r0;"
+	"*(u32*)(r10 - 4) = r0;"
+"2:"
+	/* read fp-8, should not be considered safe on second visit */
+	"r1 = *(u64*)(r10 - 8);"
+	/* use r1 in precise context */
+	"if r1 == 42 goto +0;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* stacksafe(): check if STACK_MISC in old state is considered
+ * equivalent to stack spill of a scalar in cur state.
+ */
+SEC("socket")
+__success  __log_level(2)
+__msg("8: (79) r0 = *(u64 *)(r10 -8)")
+__msg("8: safe")
+__msg("processed 11 insns")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void old_stack_misc_vs_cur_scalar(void)
+{
+	asm volatile(
+	/* get a random value for branching */
+	"call %[bpf_ktime_get_ns];"
+	"if r0 == 0 goto 1f;"
+	/* conjure STACK_{MISC,INVALID} at fp-8 */
+	"call %[bpf_ktime_get_ns];"
+	"*(u16*)(r10 - 8) = r0;"
+	"*(u16*)(r10 - 4) = r0;"
+	"goto 2f;"
+"1:"
+	/* conjure scalar at fp-8 */
+	"r0 = 42;"
+	"*(u64*)(r10 - 8) = r0;"
+"2:"
+	/* read fp-8, should be considered safe on second visit */
+	"r0 = *(u64*)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* stacksafe(): check that STACK_MISC in old state is not considered
+ * equivalent to stack spill of a non-scalar in cur state.
+ */
+SEC("socket")
+__success  __log_level(2)
+/* verifier should process exit instructions twice:
+ * - once for path entry - label 2;
+ * - once for path entry - label 1 - label 2.
+ */
+__msg("r1 = *(u64 *)(r10 -8)")
+__msg("exit")
+__msg("r1 = *(u64 *)(r10 -8)")
+__msg("exit")
+__msg("processed 11 insns")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void old_stack_misc_vs_cur_ctx_ptr(void)
+{
+	asm volatile(
+	/* remember context pointer in r9 */
+	"r9 = r1;"
+	/* get a random value for branching */
+	"call %[bpf_ktime_get_ns];"
+	"if r0 == 0 goto 1f;"
+	/* conjure STACK_MISC at fp-8 */
+	"call %[bpf_ktime_get_ns];"
+	"*(u64*)(r10 - 8) = r0;"
+	"*(u32*)(r10 - 4) = r0;"
+	"goto 2f;"
+"1:"
+	/* conjure context pointer in fp-8 */
+	"*(u64*)(r10 - 8) = r9;"
+"2:"
+	/* read fp-8, should not be considered safe on second visit */
+	"r1 = *(u64*)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_spin_lock.c b/tools/testing/selftests/bpf/progs/verifier_spin_lock.c
index 9c1aa69650..fb316c080c 100644
--- a/tools/testing/selftests/bpf/progs/verifier_spin_lock.c
+++ b/tools/testing/selftests/bpf/progs/verifier_spin_lock.c
@@ -330,7 +330,7 @@ l1_%=:	r7 = r0;					\
 
 SEC("cgroup/skb")
 __description("spin_lock: test10 lock in subprog without unlock")
-__failure __msg("unlock is missing")
+__success
 __failure_unpriv __msg_unpriv("")
 __naked void lock_in_subprog_without_unlock(void)
 {
diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
index 518329c666..7ea9785738 100644
--- a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
@@ -7,6 +7,8 @@
 #include <bpf/bpf_endian.h>
 #include <asm/errno.h>
 
+#include "bpf_compiler.h"
+
 #define TC_ACT_OK 0
 #define TC_ACT_SHOT 2
 
@@ -151,11 +153,11 @@ static __always_inline __u16 csum_ipv6_magic(const struct in6_addr *saddr,
 	__u64 sum = csum;
 	int i;
 
-#pragma unroll
+	__pragma_loop_unroll
 	for (i = 0; i < 4; i++)
 		sum += (__u32)saddr->in6_u.u6_addr32[i];
 
-#pragma unroll
+	__pragma_loop_unroll
 	for (i = 0; i < 4; i++)
 		sum += (__u32)daddr->in6_u.u6_addr32[i];
 
diff --git a/tools/testing/selftests/bpf/progs/xdping_kern.c b/tools/testing/selftests/bpf/progs/xdping_kern.c
index 54cf176511..44e2b0ef23 100644
--- a/tools/testing/selftests/bpf/progs/xdping_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdping_kern.c
@@ -15,6 +15,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+#include "bpf_compiler.h"
 #include "xdping.h"
 
 struct {
@@ -116,7 +117,7 @@ int xdping_client(struct xdp_md *ctx)
 		return XDP_PASS;
 
 	if (pinginfo->start) {
-#pragma clang loop unroll(full)
+		__pragma_loop_unroll_full
 		for (i = 0; i < XDPING_MAX_COUNT; i++) {
 			if (pinginfo->times[i] == 0)
 				break;
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index f013910212..524c38e9cd 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -181,7 +181,7 @@ static int parse_test_spec(struct test_loader *tester,
 	memset(spec, 0, sizeof(*spec));
 
 	spec->prog_name = bpf_program__name(prog);
-	spec->prog_flags = BPF_F_TEST_REG_INVARIANTS; /* by default be strict */
+	spec->prog_flags = testing_prog_flags();
 
 	btf = bpf_object__btf(obj);
 	if (!btf) {
@@ -501,7 +501,7 @@ static bool is_unpriv_capable_map(struct bpf_map *map)
 	}
 }
 
-static int do_prog_test_run(int fd_prog, int *retval)
+static int do_prog_test_run(int fd_prog, int *retval, bool empty_opts)
 {
 	__u8 tmp_out[TEST_DATA_LEN << 2] = {};
 	__u8 tmp_in[TEST_DATA_LEN] = {};
@@ -514,6 +514,10 @@ static int do_prog_test_run(int fd_prog, int *retval)
 		.repeat = 1,
 	);
 
+	if (empty_opts) {
+		memset(&topts, 0, sizeof(struct bpf_test_run_opts));
+		topts.sz = sizeof(struct bpf_test_run_opts);
+	}
 	err = bpf_prog_test_run_opts(fd_prog, &topts);
 	saved_errno = errno;
 
@@ -649,7 +653,8 @@ void run_subtest(struct test_loader *tester,
 			}
 		}
 
-		do_prog_test_run(bpf_program__fd(tprog), &retval);
+		do_prog_test_run(bpf_program__fd(tprog), &retval,
+				 bpf_program__type(tprog) == BPF_PROG_TYPE_SYSCALL ? true : false);
 		if (retval != subspec->retval && subspec->retval != POINTER_VALUE) {
 			PRINT_FAIL("Unexpected retval: %d != %d\n", retval, subspec->retval);
 			goto tobj_cleanup;
@@ -688,7 +693,7 @@ static void process_subtest(struct test_loader *tester,
 		++nr_progs;
 
 	specs = calloc(nr_progs, sizeof(struct test_spec));
-	if (!ASSERT_OK_PTR(specs, "Can't alloc specs array"))
+	if (!ASSERT_OK_PTR(specs, "specs_alloc"))
 		return;
 
 	i = 0;
diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c
index c028d621c7..d98c72dc56 100644
--- a/tools/testing/selftests/bpf/test_lpm_map.c
+++ b/tools/testing/selftests/bpf/test_lpm_map.c
@@ -211,7 +211,7 @@ static void test_lpm_map(int keysize)
 	volatile size_t n_matches, n_matches_after_delete;
 	size_t i, j, n_nodes, n_lookups;
 	struct tlpm_node *t, *list = NULL;
-	struct bpf_lpm_trie_key *key;
+	struct bpf_lpm_trie_key_u8 *key;
 	uint8_t *data, *value;
 	int r, map;
 
@@ -331,8 +331,8 @@ static void test_lpm_map(int keysize)
 static void test_lpm_ipaddr(void)
 {
 	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC);
-	struct bpf_lpm_trie_key *key_ipv4;
-	struct bpf_lpm_trie_key *key_ipv6;
+	struct bpf_lpm_trie_key_u8 *key_ipv4;
+	struct bpf_lpm_trie_key_u8 *key_ipv6;
 	size_t key_size_ipv4;
 	size_t key_size_ipv6;
 	int map_fd_ipv4;
@@ -423,7 +423,7 @@ static void test_lpm_ipaddr(void)
 static void test_lpm_delete(void)
 {
 	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC);
-	struct bpf_lpm_trie_key *key;
+	struct bpf_lpm_trie_key_u8 *key;
 	size_t key_size;
 	int map_fd;
 	__u64 value;
@@ -532,7 +532,7 @@ static void test_lpm_delete(void)
 static void test_lpm_get_next_key(void)
 {
 	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC);
-	struct bpf_lpm_trie_key *key_p, *next_key_p;
+	struct bpf_lpm_trie_key_u8 *key_p, *next_key_p;
 	size_t key_size;
 	__u32 value = 0;
 	int map_fd;
@@ -693,9 +693,9 @@ static void *lpm_test_command(void *arg)
 {
 	int i, j, ret, iter, key_size;
 	struct lpm_mt_test_info *info = arg;
-	struct bpf_lpm_trie_key *key_p;
+	struct bpf_lpm_trie_key_u8 *key_p;
 
-	key_size = sizeof(struct bpf_lpm_trie_key) + sizeof(__u32);
+	key_size = sizeof(*key_p) + sizeof(__u32);
 	key_p = alloca(key_size);
 	for (iter = 0; iter < info->iter; iter++)
 		for (i = 0; i < MAX_TEST_KEYS; i++) {
@@ -717,7 +717,7 @@ static void *lpm_test_command(void *arg)
 				ret = bpf_map_lookup_elem(info->map_fd, key_p, &value);
 				assert(ret == 0 || errno == ENOENT);
 			} else {
-				struct bpf_lpm_trie_key *next_key_p = alloca(key_size);
+				struct bpf_lpm_trie_key_u8 *next_key_p = alloca(key_size);
 				ret = bpf_map_get_next_key(info->map_fd, key_p, next_key_p);
 				assert(ret == 0 || errno == ENOENT || errno == ENOMEM);
 			}
@@ -752,7 +752,7 @@ static void test_lpm_multi_thread(void)
 
 	/* create a trie */
 	value_size = sizeof(__u32);
-	key_size = sizeof(struct bpf_lpm_trie_key) + value_size;
+	key_size = sizeof(struct bpf_lpm_trie_key_hdr) + value_size;
 	map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size, value_size, 100, &opts);
 
 	/* create 4 threads to test update, delete, lookup and get_next_key */
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 1b93878901..89ff704e9d 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -547,24 +547,6 @@ int bpf_find_map(const char *test, struct bpf_object *obj, const char *name)
 	return bpf_map__fd(map);
 }
 
-static bool is_jit_enabled(void)
-{
-	const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable";
-	bool enabled = false;
-	int sysctl_fd;
-
-	sysctl_fd = open(jit_sysctl, 0, O_RDONLY);
-	if (sysctl_fd != -1) {
-		char tmpc;
-
-		if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1)
-			enabled = (tmpc != '0');
-		close(sysctl_fd);
-	}
-
-	return enabled;
-}
-
 int compare_map_keys(int map1_fd, int map2_fd)
 {
 	__u32 key, next_key;
@@ -701,11 +683,69 @@ static const struct argp_option opts[] = {
 	{},
 };
 
+static FILE *libbpf_capture_stream;
+
+static struct {
+	char *buf;
+	size_t buf_sz;
+} libbpf_output_capture;
+
+/* Creates a global memstream capturing INFO and WARN level output
+ * passed to libbpf_print_fn.
+ * Returns 0 on success, negative value on failure.
+ * On failure the description is printed using PRINT_FAIL and
+ * current test case is marked as fail.
+ */
+int start_libbpf_log_capture(void)
+{
+	if (libbpf_capture_stream) {
+		PRINT_FAIL("%s: libbpf_capture_stream != NULL\n", __func__);
+		return -EINVAL;
+	}
+
+	libbpf_capture_stream = open_memstream(&libbpf_output_capture.buf,
+					       &libbpf_output_capture.buf_sz);
+	if (!libbpf_capture_stream) {
+		PRINT_FAIL("%s: open_memstream failed errno=%d\n", __func__, errno);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* Destroys global memstream created by start_libbpf_log_capture().
+ * Returns a pointer to captured data which has to be freed.
+ * Returned buffer is null terminated.
+ */
+char *stop_libbpf_log_capture(void)
+{
+	char *buf;
+
+	if (!libbpf_capture_stream)
+		return NULL;
+
+	fputc(0, libbpf_capture_stream);
+	fclose(libbpf_capture_stream);
+	libbpf_capture_stream = NULL;
+	/* get 'buf' after fclose(), see open_memstream() documentation */
+	buf = libbpf_output_capture.buf;
+	memset(&libbpf_output_capture, 0, sizeof(libbpf_output_capture));
+	return buf;
+}
+
 static int libbpf_print_fn(enum libbpf_print_level level,
 			   const char *format, va_list args)
 {
+	if (libbpf_capture_stream && level != LIBBPF_DEBUG) {
+		va_list args2;
+
+		va_copy(args2, args);
+		vfprintf(libbpf_capture_stream, format, args2);
+	}
+
 	if (env.verbosity < VERBOSE_VERY && level == LIBBPF_DEBUG)
 		return 0;
+
 	vfprintf(stdout, format, args);
 	return 0;
 }
@@ -1099,6 +1139,7 @@ static void run_one_test(int test_num)
 		cleanup_cgroup_environment();
 
 	stdio_restore();
+	free(stop_libbpf_log_capture());
 
 	dump_test_log(test, state, false, false, NULL);
 }
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 2f9f6f250f..0ba5a20b19 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -385,13 +385,21 @@ int test__join_cgroup(const char *path);
 			goto goto_label;				\
 	})
 
+#define ALL_TO_DEV_NULL " >/dev/null 2>&1"
+
 #define SYS_NOFAIL(fmt, ...)						\
 	({								\
 		char cmd[1024];						\
-		snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__);		\
+		int n;							\
+		n = snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__);	\
+		if (n < sizeof(cmd) && sizeof(cmd) - n >= sizeof(ALL_TO_DEV_NULL)) \
+			strcat(cmd, ALL_TO_DEV_NULL);			\
 		system(cmd);						\
 	})
 
+int start_libbpf_log_capture(void);
+char *stop_libbpf_log_capture(void);
+
 static inline __u64 ptr_to_u64(const void *ptr)
 {
 	return (__u64) (unsigned long) ptr;
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index b0068a9d2c..80c42583f5 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -19,6 +19,7 @@
 #include <bpf/libbpf.h>
 
 #include "cgroup_helpers.h"
+#include "testing_helpers.h"
 #include "bpf_util.h"
 
 #ifndef ENOTSUPP
@@ -679,7 +680,7 @@ static int load_path(const struct sock_addr_test *test, const char *path)
 
 	bpf_program__set_type(prog, BPF_PROG_TYPE_CGROUP_SOCK_ADDR);
 	bpf_program__set_expected_attach_type(prog, test->expected_attach_type);
-	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS);
+	bpf_program__set_flags(prog, testing_prog_flags());
 
 	err = bpf_object__load(obj);
 	if (err) {
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 43612de44f..024a0faafb 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -2104,9 +2104,9 @@ out:
 		free(options.whitelist);
 	if (options.blacklist)
 		free(options.blacklist);
-	close(cg_fd);
 	if (cg_created)
 		cleanup_cgroup_environment();
+	close(cg_fd);
 	return err;
 }
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index f36e41435b..df04bda1c9 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -67,6 +67,7 @@
 
 #define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS	(1 << 0)
 #define F_LOAD_WITH_STRICT_ALIGNMENT		(1 << 1)
+#define F_NEEDS_JIT_ENABLED			(1 << 2)
 
 /* need CAP_BPF, CAP_NET_ADMIN, CAP_PERFMON to load progs */
 #define ADMIN_CAPS (1ULL << CAP_NET_ADMIN |	\
@@ -74,6 +75,7 @@
 		    1ULL << CAP_BPF)
 #define UNPRIV_SYSCTL "kernel/unprivileged_bpf_disabled"
 static bool unpriv_disabled = false;
+static bool jit_disabled;
 static int skips;
 static bool verbose = false;
 static int verif_log_level = 0;
@@ -1341,48 +1343,6 @@ static bool cmp_str_seq(const char *log, const char *exp)
 	return true;
 }
 
-static struct bpf_insn *get_xlated_program(int fd_prog, int *cnt)
-{
-	__u32 buf_element_size = sizeof(struct bpf_insn);
-	struct bpf_prog_info info = {};
-	__u32 info_len = sizeof(info);
-	__u32 xlated_prog_len;
-	struct bpf_insn *buf;
-
-	if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) {
-		perror("bpf_prog_get_info_by_fd failed");
-		return NULL;
-	}
-
-	xlated_prog_len = info.xlated_prog_len;
-	if (xlated_prog_len % buf_element_size) {
-		printf("Program length %d is not multiple of %d\n",
-		       xlated_prog_len, buf_element_size);
-		return NULL;
-	}
-
-	*cnt = xlated_prog_len / buf_element_size;
-	buf = calloc(*cnt, buf_element_size);
-	if (!buf) {
-		perror("can't allocate xlated program buffer");
-		return NULL;
-	}
-
-	bzero(&info, sizeof(info));
-	info.xlated_prog_len = xlated_prog_len;
-	info.xlated_prog_insns = (__u64)(unsigned long)buf;
-	if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) {
-		perror("second bpf_prog_get_info_by_fd failed");
-		goto out_free_buf;
-	}
-
-	return buf;
-
-out_free_buf:
-	free(buf);
-	return NULL;
-}
-
 static bool is_null_insn(struct bpf_insn *insn)
 {
 	struct bpf_insn null_insn = {};
@@ -1505,7 +1465,7 @@ static void print_insn(struct bpf_insn *buf, int cnt)
 static bool check_xlated_program(struct bpf_test *test, int fd_prog)
 {
 	struct bpf_insn *buf;
-	int cnt;
+	unsigned int cnt;
 	bool result = true;
 	bool check_expected = !is_null_insn(test->expected_insns);
 	bool check_unexpected = !is_null_insn(test->unexpected_insns);
@@ -1513,8 +1473,7 @@ static bool check_xlated_program(struct bpf_test *test, int fd_prog)
 	if (!check_expected && !check_unexpected)
 		goto out;
 
-	buf = get_xlated_program(fd_prog, &cnt);
-	if (!buf) {
+	if (get_xlated_program(fd_prog, &buf, &cnt)) {
 		printf("FAIL: can't get xlated program\n");
 		result = false;
 		goto out;
@@ -1567,6 +1526,13 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	__u32 pflags;
 	int i, err;
 
+	if ((test->flags & F_NEEDS_JIT_ENABLED) && jit_disabled) {
+		printf("SKIP (requires BPF JIT)\n");
+		skips++;
+		sched_yield();
+		return;
+	}
+
 	fd_prog = -1;
 	for (i = 0; i < MAX_NR_MAPS; i++)
 		map_fds[i] = -1;
@@ -1588,7 +1554,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	if (fixup_skips != skips)
 		return;
 
-	pflags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS;
+	pflags = testing_prog_flags();
 	if (test->flags & F_LOAD_WITH_STRICT_ALIGNMENT)
 		pflags |= BPF_F_STRICT_ALIGNMENT;
 	if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)
@@ -1887,6 +1853,8 @@ int main(int argc, char **argv)
 		return EXIT_FAILURE;
 	}
 
+	jit_disabled = !is_jit_enabled();
+
 	/* Use libbpf 1.0 API mode */
 	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
 
diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c
index d2458c1b16..28b6646662 100644
--- a/tools/testing/selftests/bpf/testing_helpers.c
+++ b/tools/testing/selftests/bpf/testing_helpers.c
@@ -252,6 +252,34 @@ __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info)
 
 int extra_prog_load_log_flags = 0;
 
+int testing_prog_flags(void)
+{
+	static int cached_flags = -1;
+	static int prog_flags[] = { BPF_F_TEST_RND_HI32, BPF_F_TEST_REG_INVARIANTS };
+	static struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int insn_cnt = ARRAY_SIZE(insns), i, fd, flags = 0;
+	LIBBPF_OPTS(bpf_prog_load_opts, opts);
+
+	if (cached_flags >= 0)
+		return cached_flags;
+
+	for (i = 0; i < ARRAY_SIZE(prog_flags); i++) {
+		opts.prog_flags = prog_flags[i];
+		fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "flag-test", "GPL",
+				   insns, insn_cnt, &opts);
+		if (fd >= 0) {
+			flags |= prog_flags[i];
+			close(fd);
+		}
+	}
+
+	cached_flags = flags;
+	return cached_flags;
+}
+
 int bpf_prog_test_load(const char *file, enum bpf_prog_type type,
 		       struct bpf_object **pobj, int *prog_fd)
 {
@@ -276,7 +304,7 @@ int bpf_prog_test_load(const char *file, enum bpf_prog_type type,
 	if (type != BPF_PROG_TYPE_UNSPEC && bpf_program__type(prog) != type)
 		bpf_program__set_type(prog, type);
 
-	flags = bpf_program__flags(prog) | BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS;
+	flags = bpf_program__flags(prog) | testing_prog_flags();
 	bpf_program__set_flags(prog, flags);
 
 	err = bpf_object__load(obj);
@@ -299,7 +327,7 @@ int bpf_test_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 {
 	LIBBPF_OPTS(bpf_prog_load_opts, opts,
 		.kern_version = kern_version,
-		.prog_flags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS,
+		.prog_flags = testing_prog_flags(),
 		.log_level = extra_prog_load_log_flags,
 		.log_buf = log_buf,
 		.log_size = log_buf_sz,
@@ -328,12 +356,12 @@ __u64 read_perf_max_sample_freq(void)
 	return sample_freq;
 }
 
-static int finit_module(int fd, const char *param_values, int flags)
+int finit_module(int fd, const char *param_values, int flags)
 {
 	return syscall(__NR_finit_module, fd, param_values, flags);
 }
 
-static int delete_module(const char *name, int flags)
+int delete_module(const char *name, int flags)
 {
 	return syscall(__NR_delete_module, name, flags);
 }
@@ -387,3 +415,63 @@ int kern_sync_rcu(void)
 {
 	return syscall(__NR_membarrier, MEMBARRIER_CMD_SHARED, 0, 0);
 }
+
+int get_xlated_program(int fd_prog, struct bpf_insn **buf, __u32 *cnt)
+{
+	__u32 buf_element_size = sizeof(struct bpf_insn);
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
+	__u32 xlated_prog_len;
+
+	if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) {
+		perror("bpf_prog_get_info_by_fd failed");
+		return -1;
+	}
+
+	xlated_prog_len = info.xlated_prog_len;
+	if (xlated_prog_len % buf_element_size) {
+		printf("Program length %u is not multiple of %u\n",
+		       xlated_prog_len, buf_element_size);
+		return -1;
+	}
+
+	*cnt = xlated_prog_len / buf_element_size;
+	*buf = calloc(*cnt, buf_element_size);
+	if (!buf) {
+		perror("can't allocate xlated program buffer");
+		return -ENOMEM;
+	}
+
+	bzero(&info, sizeof(info));
+	info.xlated_prog_len = xlated_prog_len;
+	info.xlated_prog_insns = (__u64)(unsigned long)*buf;
+	if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) {
+		perror("second bpf_prog_get_info_by_fd failed");
+		goto out_free_buf;
+	}
+
+	return 0;
+
+out_free_buf:
+	free(*buf);
+	*buf = NULL;
+	return -1;
+}
+
+bool is_jit_enabled(void)
+{
+	const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable";
+	bool enabled = false;
+	int sysctl_fd;
+
+	sysctl_fd = open(jit_sysctl, O_RDONLY);
+	if (sysctl_fd != -1) {
+		char tmpc;
+
+		if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1)
+			enabled = (tmpc != '0');
+		close(sysctl_fd);
+	}
+
+	return enabled;
+}
diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h
index 35284faff4..d55f6ab124 100644
--- a/tools/testing/selftests/bpf/testing_helpers.h
+++ b/tools/testing/selftests/bpf/testing_helpers.h
@@ -36,6 +36,8 @@ __u64 read_perf_max_sample_freq(void);
 int load_bpf_testmod(bool verbose);
 int unload_bpf_testmod(bool verbose);
 int kern_sync_rcu(void);
+int finit_module(int fd, const char *param_values, int flags);
+int delete_module(const char *name, int flags);
 
 static inline __u64 get_time_ns(void)
 {
@@ -46,4 +48,12 @@ static inline __u64 get_time_ns(void)
 	return (u64)t.tv_sec * 1000000000 + t.tv_nsec;
 }
 
+struct bpf_insn;
+/* Request BPF program instructions after all rewrites are applied,
+ * e.g. verifier.c:convert_ctx_access() is done.
+ */
+int get_xlated_program(int fd_prog, struct bpf_insn **buf, __u32 *cnt);
+int testing_prog_flags(void);
+bool is_jit_enabled(void);
+
 #endif /* __TESTING_HELPERS_H */
diff --git a/tools/testing/selftests/bpf/verifier/bpf_loop_inline.c b/tools/testing/selftests/bpf/verifier/bpf_loop_inline.c
index a535d41dc2..59125b22ae 100644
--- a/tools/testing/selftests/bpf/verifier/bpf_loop_inline.c
+++ b/tools/testing/selftests/bpf/verifier/bpf_loop_inline.c
@@ -57,6 +57,7 @@
 	.expected_insns = { PSEUDO_CALL_INSN() },
 	.unexpected_insns = { HELPER_CALL_INSN() },
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_JIT_ENABLED,
 	.result = ACCEPT,
 	.runs = 0,
 	.func_info = { { 0, MAIN_TYPE }, { 12, CALLBACK_TYPE } },
@@ -90,6 +91,7 @@
 	.expected_insns = { HELPER_CALL_INSN() },
 	.unexpected_insns = { PSEUDO_CALL_INSN() },
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_JIT_ENABLED,
 	.result = ACCEPT,
 	.runs = 0,
 	.func_info = { { 0, MAIN_TYPE }, { 16, CALLBACK_TYPE } },
@@ -127,6 +129,7 @@
 	.expected_insns = { HELPER_CALL_INSN() },
 	.unexpected_insns = { PSEUDO_CALL_INSN() },
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_JIT_ENABLED,
 	.result = ACCEPT,
 	.runs = 0,
 	.func_info = {
@@ -165,6 +168,7 @@
 	.expected_insns = { PSEUDO_CALL_INSN() },
 	.unexpected_insns = { HELPER_CALL_INSN() },
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_JIT_ENABLED,
 	.result = ACCEPT,
 	.runs = 0,
 	.func_info = {
@@ -235,6 +239,7 @@
 	},
 	.unexpected_insns = { HELPER_CALL_INSN() },
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_JIT_ENABLED,
 	.result = ACCEPT,
 	.func_info = {
 		{ 0, MAIN_TYPE },
@@ -252,6 +257,7 @@
 	.unexpected_insns = { HELPER_CALL_INSN() },
 	.result = ACCEPT,
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_JIT_ENABLED,
 	.func_info = { { 0, MAIN_TYPE }, { 16, CALLBACK_TYPE } },
 	.func_info_cnt = 2,
 	BTF_TYPES
diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c
index 8a2ff81d83..0a9293a572 100644
--- a/tools/testing/selftests/bpf/verifier/precise.c
+++ b/tools/testing/selftests/bpf/verifier/precise.c
@@ -183,10 +183,10 @@
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.flags = BPF_F_TEST_STATE_FREQ,
 	.errstr = "mark_precise: frame0: last_idx 7 first_idx 7\
-	mark_precise: frame0: parent state regs=r4 stack=:\
+	mark_precise: frame0: parent state regs=r4 stack=-8:\
 	mark_precise: frame0: last_idx 6 first_idx 4\
-	mark_precise: frame0: regs=r4 stack= before 6: (b7) r0 = -1\
-	mark_precise: frame0: regs=r4 stack= before 5: (79) r4 = *(u64 *)(r10 -8)\
+	mark_precise: frame0: regs=r4 stack=-8 before 6: (b7) r0 = -1\
+	mark_precise: frame0: regs=r4 stack=-8 before 5: (79) r4 = *(u64 *)(r10 -8)\
 	mark_precise: frame0: regs= stack=-8 before 4: (7b) *(u64 *)(r3 -8) = r0\
 	mark_precise: frame0: parent state regs=r0 stack=:\
 	mark_precise: frame0: last_idx 3 first_idx 3\
diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
index 878d68db03..bdf5d81800 100644
--- a/tools/testing/selftests/bpf/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -480,7 +480,7 @@ peek:
 					for (int j = 0; j < 500; j++) {
 						if (complete_tx(xsk, clock_id))
 							break;
-						usleep(10*1000);
+						usleep(10);
 					}
 				}
 			}
-- 
cgit v1.2.3