Merge tag 'bpf-next-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Pull bpf updates from Alexei Starovoitov:

 - Introduce '__attribute__((bpf_fastcall))' for helpers and kfuncs with
   corresponding support in LLVM.

   It is similar to existing 'no_caller_saved_registers' attribute in
   GCC/LLVM with a provision for backward compatibility. It allows
   compilers generate more efficient BPF code assuming the verifier or
   JITs will inline or partially inline a helper/kfunc with such
   attribute. bpf_cast_to_kern_ctx, bpf_rdonly_cast,
   bpf_get_smp_processor_id are the first set of such helpers.

 - Harden and extend ELF build ID parsing logic.

   When called from sleepable context the relevants parts of ELF file
   will be read to find and fetch .note.gnu.build-id information. Also
   harden the logic to avoid TOCTOU, overflow, out-of-bounds problems.

 - Improvements and fixes for sched-ext:
    - Allow passing BPF iterators as kfunc arguments
    - Make the pointer returned from iter_next method trusted
    - Fix x86 JIT convergence issue due to growing/shrinking conditional
      jumps in variable length encoding

 - BPF_LSM related:
    - Introduce few VFS kfuncs and consolidate them in
      fs/bpf_fs_kfuncs.c
    - Enforce correct range of return values from certain LSM hooks
    - Disallow attaching to other LSM hooks

 - Prerequisite work for upcoming Qdisc in BPF:
    - Allow kptrs in program provided structs
    - Support for gen_epilogue in verifier_ops

 - Important fixes:
    - Fix uprobe multi pid filter check
    - Fix bpf_strtol and bpf_strtoul helpers
    - Track equal scalars history on per-instruction level
    - Fix tailcall hierarchy on x86 and arm64
    - Fix signed division overflow to prevent INT_MIN/-1 trap on x86
    - Fix get kernel stack in BPF progs attached to tracepoint:syscall

 - Selftests:
    - Add uprobe bench/stress tool
    - Generate file dependencies to drastically improve re-build time
    - Match JIT-ed and BPF asm with __xlated/__jited keywords
    - Convert older tests to test_progs framework
    - Add support for RISC-V
    - Few fixes when BPF programs are compiled with GCC-BPF backend
      (support for GCC-BPF in BPF CI is ongoing in parallel)
    - Add traffic monitor
    - Enable cross compile and musl libc

* tag 'bpf-next-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (260 commits)
  btf: require pahole 1.21+ for DEBUG_INFO_BTF with default DWARF version
  btf: move pahole check in scripts/link-vmlinux.sh to lib/Kconfig.debug
  btf: remove redundant CONFIG_BPF test in scripts/link-vmlinux.sh
  bpf: Call the missed kfree() when there is no special field in btf
  bpf: Call the missed btf_record_free() when map creation fails
  selftests/bpf: Add a test case to write mtu result into .rodata
  selftests/bpf: Add a test case to write strtol result into .rodata
  selftests/bpf: Rename ARG_PTR_TO_LONG test description
  selftests/bpf: Fix ARG_PTR_TO_LONG {half-,}uninitialized test
  bpf: Zero former ARG_PTR_TO_{LONG,INT} args in case of error
  bpf: Improve check_raw_mode_ok test for MEM_UNINIT-tagged types
  bpf: Fix helper writes to read-only maps
  bpf: Remove truncation test in bpf_strtol and bpf_strtoul helpers
  bpf: Fix bpf_strtol and bpf_strtoul helpers for 32bit
  selftests/bpf: Add tests for sdiv/smod overflow cases
  bpf: Fix a sdiv overflow issue
  libbpf: Add bpf_object__token_fd accessor
  docs/bpf: Add missing BPF program types to docs
  docs/bpf: Add constant values for linkages
  bpf: Use fake pt_regs when doing bpf syscall tracepoint tracing
  ...

176 files changed, 8560 insertions, 1661 deletions

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 5025401323af..e6533b3400de 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -8,8 +8,8 @@ test_lru_map
 test_lpm_map
 test_tag
 FEATURE-DUMP.libbpf
+FEATURE-DUMP.selftests
 fixdep
-test_dev_cgroup
 /test_progs
 /test_progs-no_alu32
 /test_progs-bpf_gcc
@@ -20,9 +20,6 @@ test_sock
 urandom_read
 test_sockmap
 test_lirc_mode2_user
-get_cgroup_id_user
-test_skb_cgroup_id_user
-test_cgroup_storage
 test_flow_dissector
 flow_dissector_load
 test_tcpnotify_user
@@ -31,6 +28,7 @@ test_tcp_check_syncookie_user
 test_sysctl
 xdping
 test_cpp
+*.d
 *.subskel.h
 *.skel.h
 *.lskel.h
diff --git a/tools/testing/selftests/bpf/DENYLIST.riscv64 b/tools/testing/selftests/bpf/DENYLIST.riscv64
new file mode 100644
index 000000000000..4fc4dfdde293
--- /dev/null
+++ b/tools/testing/selftests/bpf/DENYLIST.riscv64
@@ -0,0 +1,3 @@
+# riscv64 deny list for BPF CI and local vmtest
+exceptions					# JIT does not support exceptions
+tailcalls/tailcall_bpf2bpf*			# JIT does not support mixing bpf2bpf and tailcalls
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 81d4757ecd4c..f04af11df8eb 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -33,6 +33,13 @@ OPT_FLAGS	?= $(if $(RELEASE),-O2,-O0)
 LIBELF_CFLAGS	:= $(shell $(PKG_CONFIG) libelf --cflags 2>/dev/null)
 LIBELF_LIBS	:= $(shell $(PKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf)
 
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+endif
+
 CFLAGS += -g $(OPT_FLAGS) -rdynamic					\
 	  -Wall -Werror -fno-omit-frame-pointer				\
 	  $(GENFLAGS) $(SAN_CFLAGS) $(LIBELF_CFLAGS)			\
@@ -41,6 +48,11 @@ CFLAGS += -g $(OPT_FLAGS) -rdynamic					\
 LDFLAGS += $(SAN_LDFLAGS)
 LDLIBS += $(LIBELF_LIBS) -lz -lrt -lpthread
 
+PCAP_CFLAGS	:= $(shell $(PKG_CONFIG) --cflags libpcap 2>/dev/null && echo "-DTRAFFIC_MONITOR=1")
+PCAP_LIBS	:= $(shell $(PKG_CONFIG) --libs libpcap 2>/dev/null)
+LDLIBS += $(PCAP_LIBS)
+CFLAGS += $(PCAP_CFLAGS)
+
 # 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.
@@ -54,6 +66,10 @@ 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
 progs/test_global_func9.c-CFLAGS := -fno-strict-aliasing
+progs/verifier_nocsr.c-CFLAGS := -fno-strict-aliasing
+
+# Some utility functions use LLVM libraries
+jit_disasm_helpers.c-CFLAGS = $(LLVM_CFLAGS)
 
 ifneq ($(LLVM),)
 # Silence some warnings when compiled with clang
@@ -67,9 +83,7 @@ endif
 
 # Order correspond to 'make run_tests' order
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
-	test_dev_cgroup \
-	test_sock test_sockmap get_cgroup_id_user \
-	test_cgroup_storage \
+	test_sock test_sockmap \
 	test_tcpnotify_user test_sysctl \
 	test_progs-no_alu32
 TEST_INST_SUBDIRS := no_alu32
@@ -115,7 +129,6 @@ TEST_PROGS := test_kmod.sh \
 	test_xdp_redirect.sh \
 	test_xdp_redirect_multi.sh \
 	test_xdp_meta.sh \
-	test_xdp_veth.sh \
 	test_tunnel.sh \
 	test_lwt_seg6local.sh \
 	test_lirc_mode2.sh \
@@ -140,7 +153,7 @@ TEST_PROGS_EXTENDED := with_addr.sh \
 	test_xdp_vlan.sh test_bpftool.py
 
 # Compile but not part of 'make run_tests'
-TEST_GEN_PROGS_EXTENDED = test_skb_cgroup_id_user \
+TEST_GEN_PROGS_EXTENDED = \
 	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 \
@@ -166,6 +179,35 @@ endef
 
 include ../lib.mk
 
+NON_CHECK_FEAT_TARGETS := clean docs-clean
+CHECK_FEAT := $(filter-out $(NON_CHECK_FEAT_TARGETS),$(or $(MAKECMDGOALS), "none"))
+ifneq ($(CHECK_FEAT),)
+FEATURE_USER := .selftests
+FEATURE_TESTS := llvm
+FEATURE_DISPLAY := $(FEATURE_TESTS)
+
+# Makefile.feature expects OUTPUT to end with a slash
+ifeq ($(shell expr $(MAKE_VERSION) \>= 4.4), 1)
+$(let OUTPUT,$(OUTPUT)/,\
+	$(eval include ../../../build/Makefile.feature))
+else
+OUTPUT := $(OUTPUT)/
+$(eval include ../../../build/Makefile.feature)
+OUTPUT := $(patsubst %/,%,$(OUTPUT))
+endif
+endif
+
+ifeq ($(feature-llvm),1)
+  LLVM_CFLAGS  += -DHAVE_LLVM_SUPPORT
+  LLVM_CONFIG_LIB_COMPONENTS := mcdisassembler all-targets
+  # both llvm-config and lib.mk add -D_GNU_SOURCE, which ends up as conflict
+  LLVM_CFLAGS  += $(filter-out -D_GNU_SOURCE,$(shell $(LLVM_CONFIG) --cflags))
+  LLVM_LDLIBS  += $(shell $(LLVM_CONFIG) --link-static --libs $(LLVM_CONFIG_LIB_COMPONENTS))
+  LLVM_LDLIBS  += $(shell $(LLVM_CONFIG) --link-static --system-libs $(LLVM_CONFIG_LIB_COMPONENTS))
+  LLVM_LDLIBS  += -lstdc++
+  LLVM_LDFLAGS += $(shell $(LLVM_CONFIG) --ldflags)
+endif
+
 SCRATCH_DIR := $(OUTPUT)/tools
 BUILD_DIR := $(SCRATCH_DIR)/build
 INCLUDE_DIR := $(SCRATCH_DIR)/include
@@ -293,13 +335,9 @@ JSON_WRITER		:= $(OUTPUT)/json_writer.o
 CAP_HELPERS	:= $(OUTPUT)/cap_helpers.o
 NETWORK_HELPERS := $(OUTPUT)/network_helpers.o
 
-$(OUTPUT)/test_dev_cgroup: $(CGROUP_HELPERS) $(TESTING_HELPERS)
-$(OUTPUT)/test_skb_cgroup_id_user: $(CGROUP_HELPERS) $(TESTING_HELPERS)
 $(OUTPUT)/test_sock: $(CGROUP_HELPERS) $(TESTING_HELPERS)
 $(OUTPUT)/test_sockmap: $(CGROUP_HELPERS) $(TESTING_HELPERS)
 $(OUTPUT)/test_tcpnotify_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(TRACE_HELPERS)
-$(OUTPUT)/get_cgroup_id_user: $(CGROUP_HELPERS) $(TESTING_HELPERS)
-$(OUTPUT)/test_cgroup_storage: $(CGROUP_HELPERS) $(TESTING_HELPERS)
 $(OUTPUT)/test_sock_fields: $(CGROUP_HELPERS) $(TESTING_HELPERS)
 $(OUTPUT)/test_sysctl: $(CGROUP_HELPERS) $(TESTING_HELPERS)
 $(OUTPUT)/test_tag: $(TESTING_HELPERS)
@@ -365,10 +403,14 @@ $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
 		    DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers
 endif
 
+# vmlinux.h is first dumped to a temprorary file and then compared to
+# the previous version. This helps to avoid unnecessary re-builds of
+# $(TRUNNER_BPF_OBJS)
 $(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) | $(INCLUDE_DIR)
 ifeq ($(VMLINUX_H),)
 	$(call msg,GEN,,$@)
-	$(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@
+	$(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $(INCLUDE_DIR)/.vmlinux.h.tmp
+	$(Q)cmp -s $(INCLUDE_DIR)/.vmlinux.h.tmp $@ || mv $(INCLUDE_DIR)/.vmlinux.h.tmp $@
 else
 	$(call msg,CP,,$@)
 	$(Q)cp "$(VMLINUX_H)" $@
@@ -396,7 +438,8 @@ define get_sys_includes
 $(shell $(1) $(2) -v -E - </dev/null 2>&1 \
 	| sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \
 $(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') \
-$(shell $(1) $(2) -dM -E - </dev/null | grep '__loongarch_grlen ' | awk '{printf("-D__BITS_PER_LONG=%d", $$3)}')
+$(shell $(1) $(2) -dM -E - </dev/null | grep '__loongarch_grlen ' | awk '{printf("-D__BITS_PER_LONG=%d", $$3)}') \
+$(shell $(1) $(2) -dM -E - </dev/null | grep -E 'MIPS(EL|EB)|_MIPS_SZ(PTR|LONG) |_MIPS_SIM |_ABI(O32|N32|64) ' | awk '{printf("-D%s=%s ", $$2, $$3)}')
 endef
 
 # Determine target endianness.
@@ -427,23 +470,24 @@ $(OUTPUT)/cgroup_getset_retval_hooks.o: cgroup_getset_retval_hooks.h
 # $1 - input .c file
 # $2 - output .o file
 # $3 - CFLAGS
+# $4 - binary name
 define CLANG_BPF_BUILD_RULE
-	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
+	$(call msg,CLNG-BPF,$4,$2)
 	$(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v3 -o $2
 endef
 # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32
 define CLANG_NOALU32_BPF_BUILD_RULE
-	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
+	$(call msg,CLNG-BPF,$4,$2)
 	$(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v2 -o $2
 endef
 # Similar to CLANG_BPF_BUILD_RULE, but with cpu-v4
 define CLANG_CPUV4_BPF_BUILD_RULE
-	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
+	$(call msg,CLNG-BPF,$4,$2)
 	$(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v4 -o $2
 endef
 # Build BPF object using GCC
 define GCC_BPF_BUILD_RULE
-	$(call msg,GCC-BPF,$(TRUNNER_BINARY),$2)
+	$(call msg,GCC-BPF,$4,$2)
 	$(Q)$(BPF_GCC) $3 -DBPF_NO_PRESERVE_ACCESS_INDEX -Wno-attributes -O2 -c $1 -o $2
 endef
 
@@ -477,7 +521,14 @@ xsk_xdp_progs.skel.h-deps := xsk_xdp_progs.bpf.o
 xdp_hw_metadata.skel.h-deps := xdp_hw_metadata.bpf.o
 xdp_features.skel.h-deps := xdp_features.bpf.o
 
-LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
+LINKED_BPF_OBJS := $(foreach skel,$(LINKED_SKELS),$($(skel)-deps))
+LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(LINKED_BPF_OBJS))
+
+HEADERS_FOR_BPF_OBJS := $(wildcard $(BPFDIR)/*.bpf.h)		\
+			$(addprefix $(BPFDIR)/,	bpf_core_read.h	\
+			                        bpf_endian.h	\
+						bpf_helpers.h	\
+			                        bpf_tracing.h)
 
 # Set up extra TRUNNER_XXX "temporary" variables in the environment (relies on
 # $eval()) and pass control to DEFINE_TEST_RUNNER_RULES.
@@ -529,13 +580,12 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.bpf.o:				\
 		     $(TRUNNER_BPF_PROGS_DIR)/%.c			\
 		     $(TRUNNER_BPF_PROGS_DIR)/*.h			\
 		     $$(INCLUDE_DIR)/vmlinux.h				\
-		     $(wildcard $(BPFDIR)/bpf_*.h)			\
-		     $(wildcard $(BPFDIR)/*.bpf.h)			\
+		     $(HEADERS_FOR_BPF_OBJS)				\
 		     | $(TRUNNER_OUTPUT) $$(BPFOBJ)
 	$$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@,			\
 					  $(TRUNNER_BPF_CFLAGS)         \
 					  $$($$<-CFLAGS)		\
-					  $$($$<-$2-CFLAGS))
+					  $$($$<-$2-CFLAGS),$(TRUNNER_BINARY))
 
 $(TRUNNER_BPF_SKELS): %.skel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
@@ -556,7 +606,11 @@ $(TRUNNER_BPF_LSKELS): %.lskel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$(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) | $(TRUNNER_OUTPUT)
+$(LINKED_BPF_OBJS): %: $(TRUNNER_OUTPUT)/%
+
+# .SECONDEXPANSION here allows to correctly expand %-deps variables as prerequisites
+.SECONDEXPANSION:
+$(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_OUTPUT)/%: $$$$(%-deps) $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$$(call msg,LINK-BPF,$(TRUNNER_BINARY),$$(@:.skel.h=.bpf.o))
 	$(Q)$$(BPFTOOL) gen object $$(@:.skel.h=.linked1.o) $$(addprefix $(TRUNNER_OUTPUT)/,$$($$(@F)-deps))
 	$(Q)$$(BPFTOOL) gen object $$(@:.skel.h=.linked2.o) $$(@:.skel.h=.linked1.o)
@@ -566,6 +620,14 @@ $(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_BPF_OBJS) $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$(Q)$$(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)
+
+# When the compiler generates a %.d file, only skel basenames (not
+# full paths) are specified as prerequisites for corresponding %.o
+# file. This target makes %.skel.h basename dependent on full paths,
+# linking generated %.d dependency with actual %.skel.h files.
+$(notdir %.skel.h): $(TRUNNER_OUTPUT)/%.skel.h
+	@true
+
 endif
 
 # ensure we set up tests.h header generation rule just once
@@ -583,14 +645,25 @@ endif
 # Note: we cd into output directory to ensure embedded BPF object is found
 $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o:			\
 		      $(TRUNNER_TESTS_DIR)/%.c				\
-		      $(TRUNNER_EXTRA_HDRS)				\
-		      $(TRUNNER_BPF_OBJS)				\
-		      $(TRUNNER_BPF_SKELS)				\
-		      $(TRUNNER_BPF_LSKELS)				\
-		      $(TRUNNER_BPF_SKELS_LINKED)			\
-		      $$(BPFOBJ) | $(TRUNNER_OUTPUT)
+		      | $(TRUNNER_OUTPUT)/%.test.d
 	$$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@)
-	$(Q)cd $$(@D) && $$(CC) -I. $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F)
+	$(Q)cd $$(@D) && $$(CC) -I. $$(CFLAGS) -MMD -MT $$@ -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F)
+
+$(TRUNNER_TEST_OBJS:.o=.d): $(TRUNNER_OUTPUT)/%.test.d:			\
+			    $(TRUNNER_TESTS_DIR)/%.c			\
+			    $(TRUNNER_EXTRA_HDRS)			\
+			    $(TRUNNER_BPF_SKELS)			\
+			    $(TRUNNER_BPF_LSKELS)			\
+			    $(TRUNNER_BPF_SKELS_LINKED)			\
+			    $$(BPFOBJ) | $(TRUNNER_OUTPUT)
+
+ifeq ($(filter clean docs-clean,$(MAKECMDGOALS)),)
+include $(wildcard $(TRUNNER_TEST_OBJS:.o=.d))
+endif
+
+# add per extra obj CFGLAGS definitions
+$(foreach N,$(patsubst $(TRUNNER_OUTPUT)/%.o,%,$(TRUNNER_EXTRA_OBJS)),	\
+	$(eval $(TRUNNER_OUTPUT)/$(N).o: CFLAGS += $($(N).c-CFLAGS)))
 
 $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 		       %.c						\
@@ -608,13 +681,19 @@ ifneq ($2:$(OUTPUT),:$(shell pwd))
 	$(Q)rsync -aq $$^ $(TRUNNER_OUTPUT)/
 endif
 
+$(OUTPUT)/$(TRUNNER_BINARY): LDLIBS += $$(LLVM_LDLIBS)
+$(OUTPUT)/$(TRUNNER_BINARY): LDFLAGS += $$(LLVM_LDFLAGS)
+
+# some X.test.o files have runtime dependencies on Y.bpf.o files
+$(OUTPUT)/$(TRUNNER_BINARY): | $(TRUNNER_BPF_OBJS)
+
 $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS)			\
 			     $(TRUNNER_EXTRA_OBJS) $$(BPFOBJ)		\
 			     $(RESOLVE_BTFIDS)				\
 			     $(TRUNNER_BPFTOOL)				\
 			     | $(TRUNNER_BINARY)-extras
 	$$(call msg,BINARY,,$$@)
-	$(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@
+	$(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) $$(LDFLAGS) -o $$@
 	$(Q)$(RESOLVE_BTFIDS) --btf $(TRUNNER_OUTPUT)/btf_data.bpf.o $$@
 	$(Q)ln -sf $(if $2,..,.)/tools/build/bpftool/$(USE_BOOTSTRAP)bpftool \
 		   $(OUTPUT)/$(if $2,$2/)bpftool
@@ -633,9 +712,11 @@ TRUNNER_EXTRA_SOURCES := test_progs.c		\
 			 cap_helpers.c		\
 			 unpriv_helpers.c 	\
 			 netlink_helpers.c	\
+			 jit_disasm_helpers.c	\
 			 test_loader.c		\
 			 xsk.c			\
 			 disasm.c		\
+			 disasm_helpers.c	\
 			 json_writer.c 		\
 			 flow_dissector_load.h	\
 			 ip_check_defrag_frags.h
@@ -762,17 +843,21 @@ $(OUTPUT)/veristat: $(OUTPUT)/veristat.o
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@
 
-$(OUTPUT)/uprobe_multi: uprobe_multi.c
+# Linking uprobe_multi can fail due to relocation overflows on mips.
+$(OUTPUT)/uprobe_multi: CFLAGS += $(if $(filter mips, $(ARCH)),-mxgot)
+$(OUTPUT)/uprobe_multi: uprobe_multi.c uprobe_multi.ld
 	$(call msg,BINARY,,$@)
-	$(Q)$(CC) $(CFLAGS) -O0 $(LDFLAGS) $^ $(LDLIBS) -o $@
+	$(Q)$(CC) $(CFLAGS) -Wl,-T,uprobe_multi.ld -O0 $(LDFLAGS) 	\
+		$(filter-out %.ld,$^) $(LDLIBS) -o $@
 
 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	\
+	feature bpftool 						\
+	$(addprefix $(OUTPUT)/,*.o *.d *.skel.h *.lskel.h *.subskel.h	\
 			       no_alu32 cpuv4 bpf_gcc bpf_testmod.ko	\
 			       bpf_test_no_cfi.ko			\
-			       liburandom_read.so)
+			       liburandom_read.so)			\
+	$(OUTPUT)/FEATURE-DUMP.selftests
 
 .PHONY: docs docs-clean
 
diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index 9b974e425af3..776fbe3cb8f9 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -85,7 +85,37 @@ In case of linker errors when running selftests, try using static linking:
           If you want to change pahole and llvm, you can change `PATH` environment
           variable in the beginning of script.
 
-.. note:: The script currently only supports x86_64 and s390x architectures.
+Running vmtest on RV64
+======================
+To speed up testing and avoid various dependency issues, it is recommended to
+run vmtest in a Docker container. Before running vmtest, we need to prepare
+Docker container and local rootfs image. The overall steps are as follows:
+
+1. Create Docker container as shown in link [0].
+
+2. Use mkrootfs_debian.sh script [1] to build local rootfs image:
+
+.. code-block:: console
+
+  $ sudo ./mkrootfs_debian.sh --arch riscv64 --distro noble
+
+3. Start Docker container [0] and run vmtest in the container:
+
+.. code-block:: console
+
+  $ PLATFORM=riscv64 CROSS_COMPILE=riscv64-linux-gnu- \
+    tools/testing/selftests/bpf/vmtest.sh \
+    -l <path of local rootfs image> -- \
+    ./test_progs -d \
+        \"$(cat tools/testing/selftests/bpf/DENYLIST.riscv64 \
+            | cut -d'#' -f1 \
+            | sed -e 's/^[[:space:]]*//' \
+                  -e 's/[[:space:]]*$//' \
+            | tr -s '\n' ',' \
+        )\"
+
+Link: https://github.com/pulehui/riscv-bpf-vmtest.git [0]
+Link: https://github.com/libbpf/ci/blob/main/rootfs/mkrootfs_debian.sh [1]
 
 Additional information about selftest failures are
 documented here.
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index 627b74ae041b..1bd403a5ef7b 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -10,6 +10,7 @@
 #include <sys/sysinfo.h>
 #include <signal.h>
 #include "bench.h"
+#include "bpf_util.h"
 #include "testing_helpers.h"
 
 struct env env = {
@@ -519,6 +520,12 @@ 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_trig_uprobe_multi_nop;
+extern const struct bench bench_trig_uretprobe_multi_nop;
+extern const struct bench bench_trig_uprobe_multi_push;
+extern const struct bench bench_trig_uretprobe_multi_push;
+extern const struct bench bench_trig_uprobe_multi_ret;
+extern const struct bench bench_trig_uretprobe_multi_ret;
 
 extern const struct bench bench_rb_libbpf;
 extern const struct bench bench_rb_custom;
@@ -573,6 +580,12 @@ static const struct bench *benchs[] = {
 	&bench_trig_uretprobe_push,
 	&bench_trig_uprobe_ret,
 	&bench_trig_uretprobe_ret,
+	&bench_trig_uprobe_multi_nop,
+	&bench_trig_uretprobe_multi_nop,
+	&bench_trig_uprobe_multi_push,
+	&bench_trig_uretprobe_multi_push,
+	&bench_trig_uprobe_multi_ret,
+	&bench_trig_uretprobe_multi_ret,
 	/* ringbuf/perfbuf benchmarks */
 	&bench_rb_libbpf,
 	&bench_rb_custom,
diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h
index 68180d8f8558..005c401b3e22 100644
--- a/tools/testing/selftests/bpf/bench.h
+++ b/tools/testing/selftests/bpf/bench.h
@@ -10,6 +10,7 @@
 #include <math.h>
 #include <time.h>
 #include <sys/syscall.h>
+#include <limits.h>
 
 struct cpu_set {
 	bool *cpus;
diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
index 4b05539f167d..2ed0ef6f21ee 100644
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -276,7 +276,7 @@ static void trigger_rawtp_setup(void)
  * instructions. So use two different targets, one of which starts with nop
  * and another doesn't.
  *
- * GCC doesn't generate stack setup preample for these functions due to them
+ * GCC doesn't generate stack setup preamble for these functions due to them
  * having no input arguments and doing nothing in the body.
  */
 __nocf_check __weak void uprobe_target_nop(void)
@@ -332,7 +332,7 @@ static void *uprobe_producer_ret(void *input)
 	return NULL;
 }
 
-static void usetup(bool use_retprobe, void *target_addr)
+static void usetup(bool use_retprobe, bool use_multi, void *target_addr)
 {
 	size_t uprobe_offset;
 	struct bpf_link *link;
@@ -346,7 +346,10 @@ static void usetup(bool use_retprobe, void *target_addr)
 		exit(1);
 	}
 
-	bpf_program__set_autoload(ctx.skel->progs.bench_trigger_uprobe, true);
+	if (use_multi)
+		bpf_program__set_autoload(ctx.skel->progs.bench_trigger_uprobe_multi, true);
+	else
+		bpf_program__set_autoload(ctx.skel->progs.bench_trigger_uprobe, true);
 
 	err = trigger_bench__load(ctx.skel);
 	if (err) {
@@ -355,16 +358,28 @@ static void usetup(bool use_retprobe, void *target_addr)
 	}
 
 	uprobe_offset = get_uprobe_offset(target_addr);
-	link = bpf_program__attach_uprobe(ctx.skel->progs.bench_trigger_uprobe,
-					  use_retprobe,
-					  -1 /* all PIDs */,
-					  "/proc/self/exe",
-					  uprobe_offset);
+	if (use_multi) {
+		LIBBPF_OPTS(bpf_uprobe_multi_opts, opts,
+			.retprobe = use_retprobe,
+			.cnt = 1,
+			.offsets = &uprobe_offset,
+		);
+		link = bpf_program__attach_uprobe_multi(
+			ctx.skel->progs.bench_trigger_uprobe_multi,
+			-1 /* all PIDs */, "/proc/self/exe", NULL, &opts);
+		ctx.skel->links.bench_trigger_uprobe_multi = link;
+	} else {
+		link = bpf_program__attach_uprobe(ctx.skel->progs.bench_trigger_uprobe,
+						  use_retprobe,
+						  -1 /* all PIDs */,
+						  "/proc/self/exe",
+						  uprobe_offset);
+		ctx.skel->links.bench_trigger_uprobe = link;
+	}
 	if (!link) {
-		fprintf(stderr, "failed to attach uprobe!\n");
+		fprintf(stderr, "failed to attach %s!\n", use_multi ? "multi-uprobe" : "uprobe");
 		exit(1);
 	}
-	ctx.skel->links.bench_trigger_uprobe = link;
 }
 
 static void usermode_count_setup(void)
@@ -374,32 +389,62 @@ static void usermode_count_setup(void)
 
 static void uprobe_nop_setup(void)
 {
-	usetup(false, &uprobe_target_nop);
+	usetup(false, false /* !use_multi */, &uprobe_target_nop);
 }
 
 static void uretprobe_nop_setup(void)
 {
-	usetup(true, &uprobe_target_nop);
+	usetup(true, false /* !use_multi */, &uprobe_target_nop);
 }
 
 static void uprobe_push_setup(void)
 {
-	usetup(false, &uprobe_target_push);
+	usetup(false, false /* !use_multi */, &uprobe_target_push);
 }
 
 static void uretprobe_push_setup(void)
 {
-	usetup(true, &uprobe_target_push);
+	usetup(true, false /* !use_multi */, &uprobe_target_push);
 }
 
 static void uprobe_ret_setup(void)
 {
-	usetup(false, &uprobe_target_ret);
+	usetup(false, false /* !use_multi */, &uprobe_target_ret);
 }
 
 static void uretprobe_ret_setup(void)
 {
-	usetup(true, &uprobe_target_ret);
+	usetup(true, false /* !use_multi */, &uprobe_target_ret);
+}
+
+static void uprobe_multi_nop_setup(void)
+{
+	usetup(false, true /* use_multi */, &uprobe_target_nop);
+}
+
+static void uretprobe_multi_nop_setup(void)
+{
+	usetup(true, true /* use_multi */, &uprobe_target_nop);
+}
+
+static void uprobe_multi_push_setup(void)
+{
+	usetup(false, true /* use_multi */, &uprobe_target_push);
+}
+
+static void uretprobe_multi_push_setup(void)
+{
+	usetup(true, true /* use_multi */, &uprobe_target_push);
+}
+
+static void uprobe_multi_ret_setup(void)
+{
+	usetup(false, true /* use_multi */, &uprobe_target_ret);
+}
+
+static void uretprobe_multi_ret_setup(void)
+{
+	usetup(true, true /* use_multi */, &uprobe_target_ret);
 }
 
 const struct bench bench_trig_syscall_count = {
@@ -454,3 +499,9 @@ BENCH_TRIG_USERMODE(uprobe_ret, ret, "uprobe-ret");
 BENCH_TRIG_USERMODE(uretprobe_nop, nop, "uretprobe-nop");
 BENCH_TRIG_USERMODE(uretprobe_push, push, "uretprobe-push");
 BENCH_TRIG_USERMODE(uretprobe_ret, ret, "uretprobe-ret");
+BENCH_TRIG_USERMODE(uprobe_multi_nop, nop, "uprobe-multi-nop");
+BENCH_TRIG_USERMODE(uprobe_multi_push, push, "uprobe-multi-push");
+BENCH_TRIG_USERMODE(uprobe_multi_ret, ret, "uprobe-multi-ret");
+BENCH_TRIG_USERMODE(uretprobe_multi_nop, nop, "uretprobe-multi-nop");
+BENCH_TRIG_USERMODE(uretprobe_multi_push, push, "uretprobe-multi-push");
+BENCH_TRIG_USERMODE(uretprobe_multi_ret, ret, "uretprobe-multi-ret");
diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 828556cdc2f0..b0668f29f7b3 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -195,6 +195,32 @@ extern void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it) __ksym;
  */
 extern void bpf_throw(u64 cookie) __ksym;
 
+/* Description
+ *	Acquire a reference on the exe_file member field belonging to the
+ *	mm_struct that is nested within the supplied task_struct. The supplied
+ *	task_struct must be trusted/referenced.
+ * Returns
+ *	A referenced file pointer pointing to the exe_file member field of the
+ *	mm_struct nested in the supplied task_struct, or NULL.
+ */
+extern struct file *bpf_get_task_exe_file(struct task_struct *task) __ksym;
+
+/* Description
+ *	Release a reference on the supplied file. The supplied file must be
+ *	acquired.
+ */
+extern void bpf_put_file(struct file *file) __ksym;
+
+/* Description
+ *	Resolve a pathname for the supplied path and store it in the supplied
+ *	buffer. The supplied path must be trusted/referenced.
+ * Returns
+ *	A positive integer corresponding to the length of the resolved pathname,
+ *	including the NULL termination character, stored in the supplied
+ *	buffer. On error, a negative integer is returned.
+ */
+extern int bpf_path_d_path(struct path *path, char *buf, size_t buf__sz) __ksym;
+
 /* This macro must be used to mark the exception callback corresponding to the
  * main program. For example:
  *
diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h
index 3b6675ab4086..2eb3483f2fb0 100644
--- a/tools/testing/selftests/bpf/bpf_kfuncs.h
+++ b/tools/testing/selftests/bpf/bpf_kfuncs.h
@@ -45,7 +45,7 @@ extern int bpf_dynptr_clone(const struct bpf_dynptr *ptr, struct bpf_dynptr *clo
 
 /* Description
  *  Modify the address of a AF_UNIX sockaddr.
- * Returns__bpf_kfunc
+ * Returns
  *  -EINVAL if the address size is too big or, 0 if the sockaddr was successfully modified.
  */
 extern int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern,
@@ -78,4 +78,13 @@ extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr,
 
 extern bool bpf_session_is_return(void) __ksym __weak;
 extern __u64 *bpf_session_cookie(void) __ksym __weak;
+
+struct dentry;
+/* Description
+ *  Returns xattr of a dentry
+ * Returns
+ *  Error code
+ */
+extern int bpf_get_dentry_xattr(struct dentry *dentry, const char *name,
+			      struct bpf_dynptr *value_ptr) __ksym __weak;
 #endif
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index 22807fd78fe6..8835761d9a12 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -17,6 +17,7 @@
 #include <linux/in.h>
 #include <linux/in6.h>
 #include <linux/un.h>
+#include <linux/filter.h>
 #include <net/sock.h>
 #include <linux/namei.h>
 #include "bpf_testmod.h"
@@ -141,13 +142,12 @@ bpf_testmod_test_mod_kfunc(int i)
 
 __bpf_kfunc int bpf_iter_testmod_seq_new(struct bpf_iter_testmod_seq *it, s64 value, int cnt)
 {
-	if (cnt < 0) {
-		it->cnt = 0;
+	it->cnt = cnt;
+
+	if (cnt < 0)
 		return -EINVAL;
-	}
 
 	it->value = value;
-	it->cnt = cnt;
 
 	return 0;
 }
@@ -162,6 +162,14 @@ __bpf_kfunc s64 *bpf_iter_testmod_seq_next(struct bpf_iter_testmod_seq* it)
 	return &it->value;
 }
 
+__bpf_kfunc s64 bpf_iter_testmod_seq_value(int val, struct bpf_iter_testmod_seq* it__iter)
+{
+	if (it__iter->cnt < 0)
+		return 0;
+
+	return val + it__iter->value;
+}
+
 __bpf_kfunc void bpf_iter_testmod_seq_destroy(struct bpf_iter_testmod_seq *it)
 {
 	it->cnt = 0;
@@ -176,6 +184,36 @@ __bpf_kfunc void bpf_kfunc_dynptr_test(struct bpf_dynptr *ptr,
 {
 }
 
+__bpf_kfunc struct sk_buff *bpf_kfunc_nested_acquire_nonzero_offset_test(struct sk_buff_head *ptr)
+{
+	return NULL;
+}
+
+__bpf_kfunc struct sk_buff *bpf_kfunc_nested_acquire_zero_offset_test(struct sock_common *ptr)
+{
+	return NULL;
+}
+
+__bpf_kfunc void bpf_kfunc_nested_release_test(struct sk_buff *ptr)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_trusted_vma_test(struct vm_area_struct *ptr)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_trusted_task_test(struct task_struct *ptr)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_trusted_num_test(int *ptr)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_rcu_task_test(struct task_struct *ptr)
+{
+}
+
 __bpf_kfunc struct bpf_testmod_ctx *
 bpf_testmod_ctx_create(int *err)
 {
@@ -534,8 +572,16 @@ 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_iter_testmod_seq_value)
 BTF_ID_FLAGS(func, bpf_kfunc_common_test)
 BTF_ID_FLAGS(func, bpf_kfunc_dynptr_test)
+BTF_ID_FLAGS(func, bpf_kfunc_nested_acquire_nonzero_offset_test, KF_ACQUIRE)
+BTF_ID_FLAGS(func, bpf_kfunc_nested_acquire_zero_offset_test, KF_ACQUIRE)
+BTF_ID_FLAGS(func, bpf_kfunc_nested_release_test, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_kfunc_trusted_vma_test, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_kfunc_trusted_task_test, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_kfunc_trusted_num_test, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_kfunc_rcu_task_test, KF_RCU)
 BTF_ID_FLAGS(func, bpf_testmod_ctx_create, KF_ACQUIRE | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_testmod_ctx_release, KF_RELEASE)
 BTF_KFUNCS_END(bpf_testmod_common_kfunc_ids)
@@ -923,6 +969,51 @@ out:
 	return err;
 }
 
+static DEFINE_MUTEX(st_ops_mutex);
+static struct bpf_testmod_st_ops *st_ops;
+
+__bpf_kfunc int bpf_kfunc_st_ops_test_prologue(struct st_ops_args *args)
+{
+	int ret = -1;
+
+	mutex_lock(&st_ops_mutex);
+	if (st_ops && st_ops->test_prologue)
+		ret = st_ops->test_prologue(args);
+	mutex_unlock(&st_ops_mutex);
+
+	return ret;
+}
+
+__bpf_kfunc int bpf_kfunc_st_ops_test_epilogue(struct st_ops_args *args)
+{
+	int ret = -1;
+
+	mutex_lock(&st_ops_mutex);
+	if (st_ops && st_ops->test_epilogue)
+		ret = st_ops->test_epilogue(args);
+	mutex_unlock(&st_ops_mutex);
+
+	return ret;
+}
+
+__bpf_kfunc int bpf_kfunc_st_ops_test_pro_epilogue(struct st_ops_args *args)
+{
+	int ret = -1;
+
+	mutex_lock(&st_ops_mutex);
+	if (st_ops && st_ops->test_pro_epilogue)
+		ret = st_ops->test_pro_epilogue(args);
+	mutex_unlock(&st_ops_mutex);
+
+	return ret;
+}
+
+__bpf_kfunc int bpf_kfunc_st_ops_inc10(struct st_ops_args *args)
+{
+	args->a += 10;
+	return args->a;
+}
+
 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)
@@ -959,6 +1050,10 @@ BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_sendmsg, KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_kfunc_call_sock_sendmsg, KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_getsockname, KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_getpeername, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_prologue, KF_TRUSTED_ARGS | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_epilogue, KF_TRUSTED_ARGS | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_pro_epilogue, KF_TRUSTED_ARGS | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_st_ops_inc10, KF_TRUSTED_ARGS)
 BTF_KFUNCS_END(bpf_testmod_check_kfunc_ids)
 
 static int bpf_testmod_ops_init(struct btf *btf)
@@ -1027,6 +1122,11 @@ static void bpf_testmod_test_2(int a, int b)
 {
 }
 
+static int bpf_testmod_tramp(int value)
+{
+	return 0;
+}
+
 static int bpf_testmod_ops__test_maybe_null(int dummy,
 					    struct task_struct *task__nullable)
 {
@@ -1073,6 +1173,144 @@ struct bpf_struct_ops bpf_testmod_ops2 = {
 	.owner = THIS_MODULE,
 };
 
+static int bpf_test_mod_st_ops__test_prologue(struct st_ops_args *args)
+{
+	return 0;
+}
+
+static int bpf_test_mod_st_ops__test_epilogue(struct st_ops_args *args)
+{
+	return 0;
+}
+
+static int bpf_test_mod_st_ops__test_pro_epilogue(struct st_ops_args *args)
+{
+	return 0;
+}
+
+static int st_ops_gen_prologue(struct bpf_insn *insn_buf, bool direct_write,
+			       const struct bpf_prog *prog)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	if (strcmp(prog->aux->attach_func_name, "test_prologue") &&
+	    strcmp(prog->aux->attach_func_name, "test_pro_epilogue"))
+		return 0;
+
+	/* r6 = r1[0]; // r6 will be "struct st_ops *args". r1 is "u64 *ctx".
+	 * r7 = r6->a;
+	 * r7 += 1000;
+	 * r6->a = r7;
+	 */
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0);
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_6, offsetof(struct st_ops_args, a));
+	*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 1000);
+	*insn++ = BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_7, offsetof(struct st_ops_args, a));
+	*insn++ = prog->insnsi[0];
+
+	return insn - insn_buf;
+}
+
+static int st_ops_gen_epilogue(struct bpf_insn *insn_buf, const struct bpf_prog *prog,
+			       s16 ctx_stack_off)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	if (strcmp(prog->aux->attach_func_name, "test_epilogue") &&
+	    strcmp(prog->aux->attach_func_name, "test_pro_epilogue"))
+		return 0;
+
+	/* r1 = stack[ctx_stack_off]; // r1 will be "u64 *ctx"
+	 * r1 = r1[0]; // r1 will be "struct st_ops *args"
+	 * r6 = r1->a;
+	 * r6 += 10000;
+	 * r1->a = r6;
+	 * r0 = r6;
+	 * r0 *= 2;
+	 * BPF_EXIT;
+	 */
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_FP, ctx_stack_off);
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0);
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, offsetof(struct st_ops_args, a));
+	*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 10000);
+	*insn++ = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, offsetof(struct st_ops_args, a));
+	*insn++ = BPF_MOV64_REG(BPF_REG_0, BPF_REG_6);
+	*insn++ = BPF_ALU64_IMM(BPF_MUL, BPF_REG_0, 2);
+	*insn++ = BPF_EXIT_INSN();
+
+	return insn - insn_buf;
+}
+
+static int st_ops_btf_struct_access(struct bpf_verifier_log *log,
+				    const struct bpf_reg_state *reg,
+				    int off, int size)
+{
+	if (off < 0 || off + size > sizeof(struct st_ops_args))
+		return -EACCES;
+	return 0;
+}
+
+static const struct bpf_verifier_ops st_ops_verifier_ops = {
+	.is_valid_access = bpf_testmod_ops_is_valid_access,
+	.btf_struct_access = st_ops_btf_struct_access,
+	.gen_prologue = st_ops_gen_prologue,
+	.gen_epilogue = st_ops_gen_epilogue,
+	.get_func_proto = bpf_base_func_proto,
+};
+
+static struct bpf_testmod_st_ops st_ops_cfi_stubs = {
+	.test_prologue = bpf_test_mod_st_ops__test_prologue,
+	.test_epilogue = bpf_test_mod_st_ops__test_epilogue,
+	.test_pro_epilogue = bpf_test_mod_st_ops__test_pro_epilogue,
+};
+
+static int st_ops_reg(void *kdata, struct bpf_link *link)
+{
+	int err = 0;
+
+	mutex_lock(&st_ops_mutex);
+	if (st_ops) {
+		pr_err("st_ops has already been registered\n");
+		err = -EEXIST;
+		goto unlock;
+	}
+	st_ops = kdata;
+
+unlock:
+	mutex_unlock(&st_ops_mutex);
+	return err;
+}
+
+static void st_ops_unreg(void *kdata, struct bpf_link *link)
+{
+	mutex_lock(&st_ops_mutex);
+	st_ops = NULL;
+	mutex_unlock(&st_ops_mutex);
+}
+
+static int st_ops_init(struct btf *btf)
+{
+	return 0;
+}
+
+static int st_ops_init_member(const struct btf_type *t,
+			      const struct btf_member *member,
+			      void *kdata, const void *udata)
+{
+	return 0;
+}
+
+static struct bpf_struct_ops testmod_st_ops = {
+	.verifier_ops = &st_ops_verifier_ops,
+	.init = st_ops_init,
+	.init_member = st_ops_init_member,
+	.reg = st_ops_reg,
+	.unreg = st_ops_unreg,
+	.cfi_stubs = &st_ops_cfi_stubs,
+	.name = "bpf_testmod_st_ops",
+	.owner = THIS_MODULE,
+};
+
 extern int bpf_fentry_test1(int a);
 
 static int bpf_testmod_init(void)
@@ -1083,14 +1321,17 @@ static int bpf_testmod_init(void)
 			.kfunc_btf_id	= bpf_testmod_dtor_ids[1]
 		},
 	};
+	void **tramp;
 	int ret;
 
 	ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &bpf_testmod_common_kfunc_set);
 	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_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &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);
+	ret = ret ?: register_bpf_struct_ops(&testmod_st_ops, bpf_testmod_st_ops);
 	ret = ret ?: register_btf_id_dtor_kfuncs(bpf_testmod_dtors,
 						 ARRAY_SIZE(bpf_testmod_dtors),
 						 THIS_MODULE);
@@ -1106,6 +1347,14 @@ static int bpf_testmod_init(void)
 	ret = register_bpf_testmod_uprobe();
 	if (ret < 0)
 		return ret;
+
+	/* Ensure nothing is between tramp_1..tramp_40 */
+	BUILD_BUG_ON(offsetof(struct bpf_testmod_ops, tramp_1) + 40 * sizeof(long) !=
+		     offsetofend(struct bpf_testmod_ops, tramp_40));
+	tramp = (void **)&__bpf_testmod_ops.tramp_1;
+	while (tramp <= (void **)&__bpf_testmod_ops.tramp_40)
+		*tramp++ = bpf_testmod_tramp;
+
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
index 23fa1872ee67..fb7dff47597a 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
@@ -35,6 +35,7 @@ struct bpf_testmod_ops {
 	void (*test_2)(int a, int b);
 	/* Used to test nullable arguments. */
 	int (*test_maybe_null)(int dummy, struct task_struct *task);
+	int (*unsupported_ops)(void);
 
 	/* The following fields are used to test shadow copies. */
 	char onebyte;
@@ -93,4 +94,15 @@ struct bpf_testmod_ops2 {
 	int (*test_1)(void);
 };
 
+struct st_ops_args {
+	u64 a;
+};
+
+struct bpf_testmod_st_ops {
+	int (*test_prologue)(struct st_ops_args *args);
+	int (*test_epilogue)(struct st_ops_args *args);
+	int (*test_pro_epilogue)(struct st_ops_args *args);
+	struct module *owner;
+};
+
 #endif /* _BPF_TESTMOD_H */
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h
index e587a79f2239..b58817938deb 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h
@@ -144,4 +144,19 @@ void bpf_kfunc_dynptr_test(struct bpf_dynptr *ptr, struct bpf_dynptr *ptr__nulla
 struct bpf_testmod_ctx *bpf_testmod_ctx_create(int *err) __ksym;
 void bpf_testmod_ctx_release(struct bpf_testmod_ctx *ctx) __ksym;
 
+struct sk_buff *bpf_kfunc_nested_acquire_nonzero_offset_test(struct sk_buff_head *ptr) __ksym;
+struct sk_buff *bpf_kfunc_nested_acquire_zero_offset_test(struct sock_common *ptr) __ksym;
+void bpf_kfunc_nested_release_test(struct sk_buff *ptr) __ksym;
+
+struct st_ops_args;
+int bpf_kfunc_st_ops_test_prologue(struct st_ops_args *args) __ksym;
+int bpf_kfunc_st_ops_test_epilogue(struct st_ops_args *args) __ksym;
+int bpf_kfunc_st_ops_test_pro_epilogue(struct st_ops_args *args) __ksym;
+int bpf_kfunc_st_ops_inc10(struct st_ops_args *args) __ksym;
+
+void bpf_kfunc_trusted_vma_test(struct vm_area_struct *ptr) __ksym;
+void bpf_kfunc_trusted_task_test(struct task_struct *ptr) __ksym;
+void bpf_kfunc_trusted_num_test(int *ptr) __ksym;
+void bpf_kfunc_rcu_task_test(struct task_struct *ptr) __ksym;
+
 #endif /* _BPF_TESTMOD_KFUNC_H */
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 23bb9a9e6a7d..e4535451322e 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -644,7 +644,7 @@ unsigned long long get_classid_cgroup_id(void)
 /**
  * get_cgroup1_hierarchy_id - Retrieves the ID of a cgroup1 hierarchy from the cgroup1 subsys name.
  * @subsys_name: The cgroup1 subsys name, which can be retrieved from /proc/self/cgroup. It can be
- * a named cgroup like "name=systemd", a controller name like "net_cls", or multi-contollers like
+ * a named cgroup like "name=systemd", a controller name like "net_cls", or multi-controllers like
  * "net_cls,net_prio".
  */
 int get_cgroup1_hierarchy_id(const char *subsys_name)
diff --git a/tools/testing/selftests/bpf/config.riscv64 b/tools/testing/selftests/bpf/config.riscv64
new file mode 100644
index 000000000000..bb7043a80e1a
--- /dev/null
+++ b/tools/testing/selftests/bpf/config.riscv64
@@ -0,0 +1,84 @@
+CONFIG_AUDIT=y
+CONFIG_BLK_CGROUP=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BONDING=y
+CONFIG_BPF_JIT_ALWAYS_ON=y
+CONFIG_BPF_PRELOAD=y
+CONFIG_BPF_PRELOAD_UMD=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_HUGETLB=y
+CONFIG_CGROUP_NET_CLASSID=y
+CONFIG_CGROUP_PERF=y
+CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CPUSETS=y
+CONFIG_DEBUG_ATOMIC_SLEEP=y
+CONFIG_DEBUG_FS=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_EXPERT=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_FRAME_POINTER=y
+CONFIG_HARDLOCKUP_DETECTOR=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_HUGETLBFS=y
+CONFIG_INET=y
+CONFIG_IPV6_SEG6_LWTUNNEL=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_JUMP_LABEL=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_KPROBES=y
+CONFIG_MEMCG=y
+CONFIG_NAMESPACES=y
+CONFIG_NET=y
+CONFIG_NETDEVICES=y
+CONFIG_NETFILTER_XT_MATCH_BPF=y
+CONFIG_NET_ACT_BPF=y
+CONFIG_NET_L3_MASTER_DEV=y
+CONFIG_NET_VRF=y
+CONFIG_NONPORTABLE=y
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NR_CPUS=256
+CONFIG_PACKET=y
+CONFIG_PANIC_ON_OOPS=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_PCI=y
+CONFIG_PCI_HOST_GENERIC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_PRINTK_TIME=y
+CONFIG_PROC_KCORE=y
+CONFIG_PROFILING=y
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
+CONFIG_RISCV_EFFICIENT_UNALIGNED_ACCESS=y
+CONFIG_RISCV_ISA_C=y
+CONFIG_RISCV_PMU=y
+CONFIG_RISCV_PMU_SBI=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_SMP=y
+CONFIG_SOC_VIRT=y
+CONFIG_SYSVIPC=y
+CONFIG_TCP_CONG_ADVANCED=y
+CONFIG_TLS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_TUN=y
+CONFIG_UNIX=y
+CONFIG_UPROBES=y
+CONFIG_USER_NS=y
+CONFIG_VETH=y
+CONFIG_VLAN_8021Q=y
+CONFIG_VSOCKETS_LOOPBACK=y
+CONFIG_XFRM_USER=y
diff --git a/tools/testing/selftests/bpf/disasm_helpers.c b/tools/testing/selftests/bpf/disasm_helpers.c
new file mode 100644
index 000000000000..f529f1c8c171
--- /dev/null
+++ b/tools/testing/selftests/bpf/disasm_helpers.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+#include <bpf/bpf.h>
+#include "disasm.h"
+
+struct print_insn_context {
+	char scratch[16];
+	char *buf;
+	size_t sz;
+};
+
+static void print_insn_cb(void *private_data, const char *fmt, ...)
+{
+	struct print_insn_context *ctx = private_data;
+	va_list args;
+
+	va_start(args, fmt);
+	vsnprintf(ctx->buf, ctx->sz, fmt, args);
+	va_end(args);
+}
+
+static const char *print_call_cb(void *private_data, const struct bpf_insn *insn)
+{
+	struct print_insn_context *ctx = private_data;
+
+	/* For pseudo calls verifier.c:jit_subprogs() hides original
+	 * imm to insn->off and changes insn->imm to be an index of
+	 * the subprog instead.
+	 */
+	if (insn->src_reg == BPF_PSEUDO_CALL) {
+		snprintf(ctx->scratch, sizeof(ctx->scratch), "%+d", insn->off);
+		return ctx->scratch;
+	}
+
+	return NULL;
+}
+
+struct bpf_insn *disasm_insn(struct bpf_insn *insn, char *buf, size_t buf_sz)
+{
+	struct print_insn_context ctx = {
+		.buf = buf,
+		.sz = buf_sz,
+	};
+	struct bpf_insn_cbs cbs = {
+		.cb_print	= print_insn_cb,
+		.cb_call	= print_call_cb,
+		.private_data	= &ctx,
+	};
+	char *tmp, *pfx_end, *sfx_start;
+	bool double_insn;
+	int len;
+
+	print_bpf_insn(&cbs, insn, true);
+	/* We share code with kernel BPF disassembler, it adds '(FF) ' prefix
+	 * for each instruction (FF stands for instruction `code` byte).
+	 * Remove the prefix inplace, and also simplify call instructions.
+	 * E.g.: "(85) call foo#10" -> "call foo".
+	 * Also remove newline in the end (the 'max(strlen(buf) - 1, 0)' thing).
+	 */
+	pfx_end = buf + 5;
+	sfx_start = buf + max((int)strlen(buf) - 1, 0);
+	if (strncmp(pfx_end, "call ", 5) == 0 && (tmp = strrchr(buf, '#')))
+		sfx_start = tmp;
+	len = sfx_start - pfx_end;
+	memmove(buf, pfx_end, len);
+	buf[len] = 0;
+	double_insn = insn->code == (BPF_LD | BPF_IMM | BPF_DW);
+	return insn + (double_insn ? 2 : 1);
+}
diff --git a/tools/testing/selftests/bpf/disasm_helpers.h b/tools/testing/selftests/bpf/disasm_helpers.h
new file mode 100644
index 000000000000..7b26cab70099
--- /dev/null
+++ b/tools/testing/selftests/bpf/disasm_helpers.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+#ifndef __DISASM_HELPERS_H
+#define __DISASM_HELPERS_H
+
+#include <stdlib.h>
+
+struct bpf_insn;
+
+struct bpf_insn *disasm_insn(struct bpf_insn *insn, char *buf, size_t buf_sz);
+
+#endif /* __DISASM_HELPERS_H */
diff --git a/tools/testing/selftests/bpf/get_cgroup_id_user.c b/tools/testing/selftests/bpf/get_cgroup_id_user.c
deleted file mode 100644
index aefd83ebdcd7..000000000000
--- a/tools/testing/selftests/bpf/get_cgroup_id_user.c
+++ /dev/null
@@ -1,151 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (c) 2018 Facebook
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <errno.h>
-#include <fcntl.h>
-#include <syscall.h>
-#include <unistd.h>
-#include <linux/perf_event.h>
-#include <sys/ioctl.h>
-#include <sys/time.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-
-#include <linux/bpf.h>
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include "cgroup_helpers.h"
-#include "testing_helpers.h"
-
-#define CHECK(condition, tag, format...) ({		\
-	int __ret = !!(condition);			\
-	if (__ret) {					\
-		printf("%s:FAIL:%s ", __func__, tag);	\
-		printf(format);				\
-	} else {					\
-		printf("%s:PASS:%s\n", __func__, tag);	\
-	}						\
-	__ret;						\
-})
-
-static int bpf_find_map(const char *test, struct bpf_object *obj,
-			const char *name)
-{
-	struct bpf_map *map;
-
-	map = bpf_object__find_map_by_name(obj, name);
-	if (!map)
-		return -1;
-	return bpf_map__fd(map);
-}
-
-#define TEST_CGROUP "/test-bpf-get-cgroup-id/"
-
-int main(int argc, char **argv)
-{
-	const char *probe_name = "syscalls/sys_enter_nanosleep";
-	const char *file = "get_cgroup_id_kern.bpf.o";
-	int err, bytes, efd, prog_fd, pmu_fd;
-	int cgroup_fd, cgidmap_fd, pidmap_fd;
-	struct perf_event_attr attr = {};
-	struct bpf_object *obj;
-	__u64 kcgid = 0, ucgid;
-	__u32 key = 0, pid;
-	int exit_code = 1;
-	char buf[256];
-	const struct timespec req = {
-		.tv_sec = 1,
-		.tv_nsec = 0,
-	};
-
-	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
-	if (CHECK(cgroup_fd < 0, "cgroup_setup_and_join", "err %d errno %d\n", cgroup_fd, errno))
-		return 1;
-
-	/* Use libbpf 1.0 API mode */
-	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
-
-	err = bpf_prog_test_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
-	if (CHECK(err, "bpf_prog_test_load", "err %d errno %d\n", err, errno))
-		goto cleanup_cgroup_env;
-
-	cgidmap_fd = bpf_find_map(__func__, obj, "cg_ids");
-	if (CHECK(cgidmap_fd < 0, "bpf_find_map", "err %d errno %d\n",
-		  cgidmap_fd, errno))
-		goto close_prog;
-
-	pidmap_fd = bpf_find_map(__func__, obj, "pidmap");
-	if (CHECK(pidmap_fd < 0, "bpf_find_map", "err %d errno %d\n",
-		  pidmap_fd, errno))
-		goto close_prog;
-
-	pid = getpid();
-	bpf_map_update_elem(pidmap_fd, &key, &pid, 0);
-
-	if (access("/sys/kernel/tracing/trace", F_OK) == 0) {
-		snprintf(buf, sizeof(buf),
-			 "/sys/kernel/tracing/events/%s/id", probe_name);
-	} else {
-		snprintf(buf, sizeof(buf),
-			 "/sys/kernel/debug/tracing/events/%s/id", probe_name);
-	}
-	efd = open(buf, O_RDONLY, 0);
-	if (CHECK(efd < 0, "open", "err %d errno %d\n", efd, errno))
-		goto close_prog;
-	bytes = read(efd, buf, sizeof(buf));
-	close(efd);
-	if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "read",
-		  "bytes %d errno %d\n", bytes, errno))
-		goto close_prog;
-
-	attr.config = strtol(buf, NULL, 0);
-	attr.type = PERF_TYPE_TRACEPOINT;
-	attr.sample_type = PERF_SAMPLE_RAW;
-	attr.sample_period = 1;
-	attr.wakeup_events = 1;
-
-	/* attach to this pid so the all bpf invocations will be in the
-	 * cgroup associated with this pid.
-	 */
-	pmu_fd = syscall(__NR_perf_event_open, &attr, getpid(), -1, -1, 0);
-	if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd,
-		  errno))
-		goto close_prog;
-
-	err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
-	if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n", err,
-		  errno))
-		goto close_pmu;
-
-	err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
-	if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n", err,
-		  errno))
-		goto close_pmu;
-
-	/* trigger some syscalls */
-	syscall(__NR_nanosleep, &req, NULL);
-
-	err = bpf_map_lookup_elem(cgidmap_fd, &key, &kcgid);
-	if (CHECK(err, "bpf_map_lookup_elem", "err %d errno %d\n", err, errno))
-		goto close_pmu;
-
-	ucgid = get_cgroup_id(TEST_CGROUP);
-	if (CHECK(kcgid != ucgid, "compare_cgroup_id",
-		  "kern cgid %llx user cgid %llx", kcgid, ucgid))
-		goto close_pmu;
-
-	exit_code = 0;
-	printf("%s:PASS\n", argv[0]);
-
-close_pmu:
-	close(pmu_fd);
-close_prog:
-	bpf_object__close(obj);
-cleanup_cgroup_env:
-	cleanup_cgroup_environment();
-	return exit_code;
-}
diff --git a/tools/testing/selftests/bpf/jit_disasm_helpers.c b/tools/testing/selftests/bpf/jit_disasm_helpers.c
new file mode 100644
index 000000000000..febd6b12e372
--- /dev/null
+++ b/tools/testing/selftests/bpf/jit_disasm_helpers.c
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <test_progs.h>
+
+#ifdef HAVE_LLVM_SUPPORT
+
+#include <llvm-c/Core.h>
+#include <llvm-c/Disassembler.h>
+#include <llvm-c/Target.h>
+#include <llvm-c/TargetMachine.h>
+
+/* The intent is to use get_jited_program_text() for small test
+ * programs written in BPF assembly, thus assume that 32 local labels
+ * would be sufficient.
+ */
+#define MAX_LOCAL_LABELS 32
+
+/* Local labels are encoded as 'L42', this requires 4 bytes of storage:
+ * 3 characters + zero byte
+ */
+#define LOCAL_LABEL_LEN 4
+
+static bool llvm_initialized;
+
+struct local_labels {
+	bool print_phase;
+	__u32 prog_len;
+	__u32 cnt;
+	__u32 pcs[MAX_LOCAL_LABELS];
+	char names[MAX_LOCAL_LABELS][LOCAL_LABEL_LEN];
+};
+
+static const char *lookup_symbol(void *data, uint64_t ref_value, uint64_t *ref_type,
+				 uint64_t ref_pc, const char **ref_name)
+{
+	struct local_labels *labels = data;
+	uint64_t type = *ref_type;
+	int i;
+
+	*ref_type = LLVMDisassembler_ReferenceType_InOut_None;
+	*ref_name = NULL;
+	if (type != LLVMDisassembler_ReferenceType_In_Branch)
+		return NULL;
+	/* Depending on labels->print_phase either discover local labels or
+	 * return a name assigned with local jump target:
+	 * - if print_phase is true and ref_value is in labels->pcs,
+	 *   return corresponding labels->name.
+	 * - if print_phase is false, save program-local jump targets
+	 *   in labels->pcs;
+	 */
+	if (labels->print_phase) {
+		for (i = 0; i < labels->cnt; ++i)
+			if (labels->pcs[i] == ref_value)
+				return labels->names[i];
+	} else {
+		if (labels->cnt < MAX_LOCAL_LABELS && ref_value < labels->prog_len)
+			labels->pcs[labels->cnt++] = ref_value;
+	}
+	return NULL;
+}
+
+static int disasm_insn(LLVMDisasmContextRef ctx, uint8_t *image, __u32 len, __u32 pc,
+		       char *buf, __u32 buf_sz)
+{
+	int i, cnt;
+
+	cnt = LLVMDisasmInstruction(ctx, image + pc, len - pc, pc,
+				    buf, buf_sz);
+	if (cnt > 0)
+		return cnt;
+	PRINT_FAIL("Can't disasm instruction at offset %d:", pc);
+	for (i = 0; i < 16 && pc + i < len; ++i)
+		printf(" %02x", image[pc + i]);
+	printf("\n");
+	return -EINVAL;
+}
+
+static int cmp_u32(const void *_a, const void *_b)
+{
+	__u32 a = *(__u32 *)_a;
+	__u32 b = *(__u32 *)_b;
+
+	if (a < b)
+		return -1;
+	if (a > b)
+		return 1;
+	return 0;
+}
+
+static int disasm_one_func(FILE *text_out, uint8_t *image, __u32 len)
+{
+	char *label, *colon, *triple = NULL;
+	LLVMDisasmContextRef ctx = NULL;
+	struct local_labels labels = {};
+	__u32 *label_pc, pc;
+	int i, cnt, err = 0;
+	char buf[64];
+
+	triple = LLVMGetDefaultTargetTriple();
+	ctx = LLVMCreateDisasm(triple, &labels, 0, NULL, lookup_symbol);
+	if (!ASSERT_OK_PTR(ctx, "LLVMCreateDisasm")) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	cnt = LLVMSetDisasmOptions(ctx, LLVMDisassembler_Option_PrintImmHex);
+	if (!ASSERT_EQ(cnt, 1, "LLVMSetDisasmOptions")) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	/* discover labels */
+	labels.prog_len = len;
+	pc = 0;
+	while (pc < len) {
+		cnt = disasm_insn(ctx, image, len, pc, buf, 1);
+		if (cnt < 0) {
+			err = cnt;
+			goto out;
+		}
+		pc += cnt;
+	}
+	qsort(labels.pcs, labels.cnt, sizeof(*labels.pcs), cmp_u32);
+	for (i = 0; i < labels.cnt; ++i)
+		/* gcc is unable to infer upper bound for labels.cnt and assumes
+		 * it to be U32_MAX. U32_MAX takes 10 decimal digits.
+		 * snprintf below prints into labels.names[*],
+		 * which has space only for two digits and a letter.
+		 * To avoid truncation warning use (i % MAX_LOCAL_LABELS),
+		 * which informs gcc about printed value upper bound.
+		 */
+		snprintf(labels.names[i], sizeof(labels.names[i]), "L%d", i % MAX_LOCAL_LABELS);
+
+	/* now print with labels */
+	labels.print_phase = true;
+	pc = 0;
+	while (pc < len) {
+		cnt = disasm_insn(ctx, image, len, pc, buf, sizeof(buf));
+		if (cnt < 0) {
+			err = cnt;
+			goto out;
+		}
+		label_pc = bsearch(&pc, labels.pcs, labels.cnt, sizeof(*labels.pcs), cmp_u32);
+		label = "";
+		colon = "";
+		if (label_pc) {
+			label = labels.names[label_pc - labels.pcs];
+			colon = ":";
+		}
+		fprintf(text_out, "%x:\t", pc);
+		for (i = 0; i < cnt; ++i)
+			fprintf(text_out, "%02x ", image[pc + i]);
+		for (i = cnt * 3; i < 12 * 3; ++i)
+			fputc(' ', text_out);
+		fprintf(text_out, "%s%s%s\n", label, colon, buf);
+		pc += cnt;
+	}
+
+out:
+	if (triple)
+		LLVMDisposeMessage(triple);
+	if (ctx)
+		LLVMDisasmDispose(ctx);
+	return err;
+}
+
+int get_jited_program_text(int fd, char *text, size_t text_sz)
+{
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
+	__u32 jited_funcs, len, pc;
+	__u32 *func_lens = NULL;
+	FILE *text_out = NULL;
+	uint8_t *image = NULL;
+	int i, err = 0;
+
+	if (!llvm_initialized) {
+		LLVMInitializeAllTargetInfos();
+		LLVMInitializeAllTargetMCs();
+		LLVMInitializeAllDisassemblers();
+		llvm_initialized = 1;
+	}
+
+	text_out = fmemopen(text, text_sz, "w");
+	if (!ASSERT_OK_PTR(text_out, "open_memstream")) {
+		err = -errno;
+		goto out;
+	}
+
+	/* first call is to find out jited program len */
+	err = bpf_prog_get_info_by_fd(fd, &info, &info_len);
+	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd #1"))
+		goto out;
+
+	len = info.jited_prog_len;
+	image = malloc(len);
+	if (!ASSERT_OK_PTR(image, "malloc(info.jited_prog_len)")) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	jited_funcs = info.nr_jited_func_lens;
+	func_lens = malloc(jited_funcs * sizeof(__u32));
+	if (!ASSERT_OK_PTR(func_lens, "malloc(info.nr_jited_func_lens)")) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	memset(&info, 0, sizeof(info));
+	info.jited_prog_insns = (__u64)image;
+	info.jited_prog_len = len;
+	info.jited_func_lens = (__u64)func_lens;
+	info.nr_jited_func_lens = jited_funcs;
+	err = bpf_prog_get_info_by_fd(fd, &info, &info_len);
+	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd #2"))
+		goto out;
+
+	for (pc = 0, i = 0; i < jited_funcs; ++i) {
+		fprintf(text_out, "func #%d:\n", i);
+		disasm_one_func(text_out, image + pc, func_lens[i]);
+		fprintf(text_out, "\n");
+		pc += func_lens[i];
+	}
+
+out:
+	if (text_out)
+		fclose(text_out);
+	if (image)
+		free(image);
+	if (func_lens)
+		free(func_lens);
+	return err;
+}
+
+#else /* HAVE_LLVM_SUPPORT */
+
+int get_jited_program_text(int fd, char *text, size_t text_sz)
+{
+	if (env.verbosity >= VERBOSE_VERY)
+		printf("compiled w/o llvm development libraries, can't dis-assembly binary code");
+	return -EOPNOTSUPP;
+}
+
+#endif /* HAVE_LLVM_SUPPORT */
diff --git a/tools/testing/selftests/bpf/jit_disasm_helpers.h b/tools/testing/selftests/bpf/jit_disasm_helpers.h
new file mode 100644
index 000000000000..e6924fd65ecf
--- /dev/null
+++ b/tools/testing/selftests/bpf/jit_disasm_helpers.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+#ifndef __JIT_DISASM_HELPERS_H
+#define __JIT_DISASM_HELPERS_H
+
+#include <stddef.h>
+
+int get_jited_program_text(int fd, char *text, size_t text_sz);
+
+#endif /* __JIT_DISASM_HELPERS_H */
diff --git a/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c
index 1230ccf90128..5da493b94ae2 100644
--- a/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c
+++ b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c
@@ -197,7 +197,7 @@ void __test_map_lookup_and_delete_batch(bool is_pcpu)
 		CHECK(total != max_entries, "delete with steps",
 		      "total = %u, max_entries = %u\n", total, max_entries);
 
-		/* check map is empty, errono == ENOENT */
+		/* check map is empty, errno == ENOENT */
 		err = bpf_map_get_next_key(map_fd, NULL, &key);
 		CHECK(!err || errno != ENOENT, "bpf_map_get_next_key()",
 		      "error: %s\n", strerror(errno));
diff --git a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c
index b66d56ddb7ef..fe3e19f96244 100644
--- a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c
+++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c
@@ -135,7 +135,7 @@ void test_lpm_trie_map_batch_ops(void)
 		CHECK(total != max_entries, "delete with steps",
 		      "total = %u, max_entries = %u\n", total, max_entries);
 
-		/* check map is empty, errono == ENOENT */
+		/* check map is empty, errno == ENOENT */
 		err = bpf_map_get_next_key(map_fd, NULL, &key);
 		CHECK(!err || errno != ENOENT, "bpf_map_get_next_key()",
 		      "error: %s\n", strerror(errno));
diff --git a/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
index 2ea36408816b..1c7c04288eff 100644
--- a/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
+++ b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
@@ -17,6 +17,7 @@
 #define MAX_ENTRIES_HASH_OF_MAPS	64
 #define N_THREADS			8
 #define MAX_MAP_KEY_SIZE		4
+#define PCPU_MIN_UNIT_SIZE		32768
 
 static void map_info(int map_fd, struct bpf_map_info *info)
 {
@@ -456,6 +457,22 @@ static void map_percpu_stats_hash_of_maps(void)
 	printf("test_%s:PASS\n", __func__);
 }
 
+static void map_percpu_stats_map_value_size(void)
+{
+	int fd;
+	int value_sz = PCPU_MIN_UNIT_SIZE + 1;
+	struct bpf_map_create_opts opts = { .sz = sizeof(opts) };
+	enum bpf_map_type map_types[] = { BPF_MAP_TYPE_PERCPU_ARRAY,
+					  BPF_MAP_TYPE_PERCPU_HASH,
+					  BPF_MAP_TYPE_LRU_PERCPU_HASH };
+	for (int i = 0; i < ARRAY_SIZE(map_types); i++) {
+		fd = bpf_map_create(map_types[i], NULL, sizeof(__u32), value_sz, 1, &opts);
+		CHECK(fd < 0 && errno != E2BIG, "percpu map value size",
+			"error: %s\n", strerror(errno));
+	}
+	printf("test_%s:PASS\n", __func__);
+}
+
 void test_map_percpu_stats(void)
 {
 	map_percpu_stats_hash();
@@ -467,4 +484,5 @@ void test_map_percpu_stats(void)
 	map_percpu_stats_percpu_lru_hash();
 	map_percpu_stats_percpu_lru_hash_no_common();
 	map_percpu_stats_hash_of_maps();
+	map_percpu_stats_map_value_size();
 }
diff --git a/tools/testing/selftests/bpf/map_tests/sk_storage_map.c b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c
index 18405c3b7cee..af10c309359a 100644
--- a/tools/testing/selftests/bpf/map_tests/sk_storage_map.c
+++ b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c
@@ -412,7 +412,7 @@ static void test_sk_storage_map_stress_free(void)
 		rlim_new.rlim_max = rlim_new.rlim_cur + 128;
 		err = setrlimit(RLIMIT_NOFILE, &rlim_new);
 		CHECK(err, "setrlimit(RLIMIT_NOFILE)", "rlim_new:%lu errno:%d",
-		      rlim_new.rlim_cur, errno);
+		      (unsigned long) rlim_new.rlim_cur, errno);
 	}
 
 	err = do_sk_storage_map_stress_free();
diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index e0cba4178e41..27784946b01b 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -11,17 +11,31 @@
 #include <arpa/inet.h>
 #include <sys/mount.h>
 #include <sys/stat.h>
+#include <sys/types.h>
 #include <sys/un.h>
+#include <sys/eventfd.h>
 
 #include <linux/err.h>
 #include <linux/in.h>
 #include <linux/in6.h>
 #include <linux/limits.h>
 
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <netinet/tcp.h>
+#include <net/if.h>
+
 #include "bpf_util.h"
 #include "network_helpers.h"
 #include "test_progs.h"
 
+#ifdef TRAFFIC_MONITOR
+/* Prevent pcap.h from including pcap/bpf.h and causing conflicts */
+#define PCAP_DONT_INCLUDE_PCAP_BPF_H 1
+#include <pcap/pcap.h>
+#include <pcap/dlt.h>
+#endif
+
 #ifndef IPPROTO_MPTCP
 #define IPPROTO_MPTCP 262
 #endif
@@ -80,12 +94,15 @@ int settimeo(int fd, int timeout_ms)
 
 #define save_errno_close(fd) ({ int __save = errno; close(fd); errno = __save; })
 
-static int __start_server(int type, const struct sockaddr *addr, socklen_t addrlen,
-			  const struct network_helper_opts *opts)
+int start_server_addr(int type, const struct sockaddr_storage *addr, socklen_t addrlen,
+		      const struct network_helper_opts *opts)
 {
 	int fd;
 
-	fd = socket(addr->sa_family, type, opts->proto);
+	if (!opts)
+		opts = &default_opts;
+
+	fd = socket(addr->ss_family, type, opts->proto);
 	if (fd < 0) {
 		log_err("Failed to create server socket");
 		return -1;
@@ -100,7 +117,7 @@ static int __start_server(int type, const struct sockaddr *addr, socklen_t addrl
 		goto error_close;
 	}
 
-	if (bind(fd, addr, addrlen) < 0) {
+	if (bind(fd, (struct sockaddr *)addr, addrlen) < 0) {
 		log_err("Failed to bind socket");
 		goto error_close;
 	}
@@ -131,7 +148,7 @@ int start_server_str(int family, int type, const char *addr_str, __u16 port,
 	if (make_sockaddr(family, addr_str, port, &addr, &addrlen))
 		return -1;
 
-	return __start_server(type, (struct sockaddr *)&addr, addrlen, opts);
+	return start_server_addr(type, &addr, addrlen, opts);
 }
 
 int start_server(int family, int type, const char *addr_str, __u16 port,
@@ -173,7 +190,7 @@ int *start_reuseport_server(int family, int type, const char *addr_str,
 	if (!fds)
 		return NULL;
 
-	fds[0] = __start_server(type, (struct sockaddr *)&addr, addrlen, &opts);
+	fds[0] = start_server_addr(type, &addr, addrlen, &opts);
 	if (fds[0] == -1)
 		goto close_fds;
 	nr_fds = 1;
@@ -182,7 +199,7 @@ int *start_reuseport_server(int family, int type, const char *addr_str,
 		goto close_fds;
 
 	for (; nr_fds < nr_listens; nr_fds++) {
-		fds[nr_fds] = __start_server(type, (struct sockaddr *)&addr, addrlen, &opts);
+		fds[nr_fds] = start_server_addr(type, &addr, addrlen, &opts);
 		if (fds[nr_fds] == -1)
 			goto close_fds;
 	}
@@ -194,15 +211,6 @@ close_fds:
 	return NULL;
 }
 
-int start_server_addr(int type, const struct sockaddr_storage *addr, socklen_t len,
-		      const struct network_helper_opts *opts)
-{
-	if (!opts)
-		opts = &default_opts;
-
-	return __start_server(type, (struct sockaddr *)addr, len, opts);
-}
-
 void free_fds(int *fds, unsigned int nr_close_fds)
 {
 	if (fds) {
@@ -277,33 +285,6 @@ error_close:
 	return -1;
 }
 
-static int connect_fd_to_addr(int fd,
-			      const struct sockaddr_storage *addr,
-			      socklen_t addrlen, const bool must_fail)
-{
-	int ret;
-
-	errno = 0;
-	ret = connect(fd, (const struct sockaddr *)addr, addrlen);
-	if (must_fail) {
-		if (!ret) {
-			log_err("Unexpected success to connect to server");
-			return -1;
-		}
-		if (errno != EPERM) {
-			log_err("Unexpected error from connect to server");
-			return -1;
-		}
-	} else {
-		if (ret) {
-			log_err("Failed to connect to server");
-			return -1;
-		}
-	}
-
-	return 0;
-}
-
 int connect_to_addr(int type, const struct sockaddr_storage *addr, socklen_t addrlen,
 		    const struct network_helper_opts *opts)
 {
@@ -318,17 +299,17 @@ int connect_to_addr(int type, const struct sockaddr_storage *addr, socklen_t add
 		return -1;
 	}
 
-	if (connect_fd_to_addr(fd, addr, addrlen, opts->must_fail))
-		goto error_close;
+	if (connect(fd, (const struct sockaddr *)addr, addrlen)) {
+		log_err("Failed to connect to server");
+		save_errno_close(fd);
+		return -1;
+	}
 
 	return fd;
-
-error_close:
-	save_errno_close(fd);
-	return -1;
 }
 
-int connect_to_fd_opts(int server_fd, int type, const struct network_helper_opts *opts)
+int connect_to_addr_str(int family, int type, const char *addr_str, __u16 port,
+			const struct network_helper_opts *opts)
 {
 	struct sockaddr_storage addr;
 	socklen_t addrlen;
@@ -336,6 +317,27 @@ int connect_to_fd_opts(int server_fd, int type, const struct network_helper_opts
 	if (!opts)
 		opts = &default_opts;
 
+	if (make_sockaddr(family, addr_str, port, &addr, &addrlen))
+		return -1;
+
+	return connect_to_addr(type, &addr, addrlen, opts);
+}
+
+int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts)
+{
+	struct sockaddr_storage addr;
+	socklen_t addrlen, optlen;
+	int type;
+
+	if (!opts)
+		opts = &default_opts;
+
+	optlen = sizeof(type);
+	if (getsockopt(server_fd, SOL_SOCKET, SO_TYPE, &type, &optlen)) {
+		log_err("getsockopt(SOL_TYPE)");
+		return -1;
+	}
+
 	addrlen = sizeof(addr);
 	if (getsockname(server_fd, (struct sockaddr *)&addr, &addrlen)) {
 		log_err("Failed to get server addr");
@@ -350,14 +352,8 @@ int connect_to_fd(int server_fd, int timeout_ms)
 	struct network_helper_opts opts = {
 		.timeout_ms = timeout_ms,
 	};
-	int type, protocol;
 	socklen_t optlen;
-
-	optlen = sizeof(type);
-	if (getsockopt(server_fd, SOL_SOCKET, SO_TYPE, &type, &optlen)) {
-		log_err("getsockopt(SOL_TYPE)");
-		return -1;
-	}
+	int protocol;
 
 	optlen = sizeof(protocol);
 	if (getsockopt(server_fd, SOL_SOCKET, SO_PROTOCOL, &protocol, &optlen)) {
@@ -366,7 +362,7 @@ int connect_to_fd(int server_fd, int timeout_ms)
 	}
 	opts.proto = protocol;
 
-	return connect_to_fd_opts(server_fd, type, &opts);
+	return connect_to_fd_opts(server_fd, &opts);
 }
 
 int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms)
@@ -382,8 +378,10 @@ int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms)
 		return -1;
 	}
 
-	if (connect_fd_to_addr(client_fd, &addr, len, false))
+	if (connect(client_fd, (const struct sockaddr *)&addr, len)) {
+		log_err("Failed to connect to server");
 		return -1;
+	}
 
 	return 0;
 }
@@ -448,6 +446,52 @@ char *ping_command(int family)
 	return "ping";
 }
 
+int remove_netns(const char *name)
+{
+	char *cmd;
+	int r;
+
+	r = asprintf(&cmd, "ip netns del %s >/dev/null 2>&1", name);
+	if (r < 0) {
+		log_err("Failed to malloc cmd");
+		return -1;
+	}
+
+	r = system(cmd);
+	free(cmd);
+	return r;
+}
+
+int make_netns(const char *name)
+{
+	char *cmd;
+	int r;
+
+	r = asprintf(&cmd, "ip netns add %s", name);
+	if (r < 0) {
+		log_err("Failed to malloc cmd");
+		return -1;
+	}
+
+	r = system(cmd);
+	free(cmd);
+
+	if (r)
+		return r;
+
+	r = asprintf(&cmd, "ip -n %s link set lo up", name);
+	if (r < 0) {
+		log_err("Failed to malloc cmd for setting up lo");
+		remove_netns(name);
+		return -1;
+	}
+
+	r = system(cmd);
+	free(cmd);
+
+	return r;
+}
+
 struct nstoken {
 	int orig_netns_fd;
 };
@@ -676,3 +720,443 @@ int send_recv_data(int lfd, int fd, uint32_t total_bytes)
 
 	return err;
 }
+
+#ifdef TRAFFIC_MONITOR
+struct tmonitor_ctx {
+	pcap_t *pcap;
+	pcap_dumper_t *dumper;
+	pthread_t thread;
+	int wake_fd;
+
+	volatile bool done;
+	char pkt_fname[PATH_MAX];
+	int pcap_fd;
+};
+
+/* Is this packet captured with a Ethernet protocol type? */
+static bool is_ethernet(const u_char *packet)
+{
+	u16 arphdr_type;
+
+	memcpy(&arphdr_type, packet + 8, 2);
+	arphdr_type = ntohs(arphdr_type);
+
+	/* Except the following cases, the protocol type contains the
+	 * Ethernet protocol type for the packet.
+	 *
+	 * https://www.tcpdump.org/linktypes/LINKTYPE_LINUX_SLL2.html
+	 */
+	switch (arphdr_type) {
+	case 770: /* ARPHRD_FRAD */
+	case 778: /* ARPHDR_IPGRE */
+	case 803: /* ARPHRD_IEEE80211_RADIOTAP */
+		printf("Packet captured: arphdr_type=%d\n", arphdr_type);
+		return false;
+	}
+	return true;
+}
+
+static const char * const pkt_types[] = {
+	"In",
+	"B",			/* Broadcast */
+	"M",			/* Multicast */
+	"C",			/* Captured with the promiscuous mode */
+	"Out",
+};
+
+static const char *pkt_type_str(u16 pkt_type)
+{
+	if (pkt_type < ARRAY_SIZE(pkt_types))
+		return pkt_types[pkt_type];
+	return "Unknown";
+}
+
+/* Show the information of the transport layer in the packet */
+static void show_transport(const u_char *packet, u16 len, u32 ifindex,
+			   const char *src_addr, const char *dst_addr,
+			   u16 proto, bool ipv6, u8 pkt_type)
+{
+	char *ifname, _ifname[IF_NAMESIZE];
+	const char *transport_str;
+	u16 src_port, dst_port;
+	struct udphdr *udp;
+	struct tcphdr *tcp;
+
+	ifname = if_indextoname(ifindex, _ifname);
+	if (!ifname) {
+		snprintf(_ifname, sizeof(_ifname), "unknown(%d)", ifindex);
+		ifname = _ifname;
+	}
+
+	if (proto == IPPROTO_UDP) {
+		udp = (struct udphdr *)packet;
+		src_port = ntohs(udp->source);
+		dst_port = ntohs(udp->dest);
+		transport_str = "UDP";
+	} else if (proto == IPPROTO_TCP) {
+		tcp = (struct tcphdr *)packet;
+		src_port = ntohs(tcp->source);
+		dst_port = ntohs(tcp->dest);
+		transport_str = "TCP";
+	} else if (proto == IPPROTO_ICMP) {
+		printf("%-7s %-3s IPv4 %s > %s: ICMP, length %d, type %d, code %d\n",
+		       ifname, pkt_type_str(pkt_type), src_addr, dst_addr, len,
+		       packet[0], packet[1]);
+		return;
+	} else if (proto == IPPROTO_ICMPV6) {
+		printf("%-7s %-3s IPv6 %s > %s: ICMPv6, length %d, type %d, code %d\n",
+		       ifname, pkt_type_str(pkt_type), src_addr, dst_addr, len,
+		       packet[0], packet[1]);
+		return;
+	} else {
+		printf("%-7s %-3s %s %s > %s: protocol %d\n",
+		       ifname, pkt_type_str(pkt_type), ipv6 ? "IPv6" : "IPv4",
+		       src_addr, dst_addr, proto);
+		return;
+	}
+
+	/* TCP or UDP*/
+
+	flockfile(stdout);
+	if (ipv6)
+		printf("%-7s %-3s IPv6 %s.%d > %s.%d: %s, length %d",
+		       ifname, pkt_type_str(pkt_type), src_addr, src_port,
+		       dst_addr, dst_port, transport_str, len);
+	else
+		printf("%-7s %-3s IPv4 %s:%d > %s:%d: %s, length %d",
+		       ifname, pkt_type_str(pkt_type), src_addr, src_port,
+		       dst_addr, dst_port, transport_str, len);
+
+	if (proto == IPPROTO_TCP) {
+		if (tcp->fin)
+			printf(", FIN");
+		if (tcp->syn)
+			printf(", SYN");
+		if (tcp->rst)
+			printf(", RST");
+		if (tcp->ack)
+			printf(", ACK");
+	}
+
+	printf("\n");
+	funlockfile(stdout);
+}
+
+static void show_ipv6_packet(const u_char *packet, u32 ifindex, u8 pkt_type)
+{
+	char src_buf[INET6_ADDRSTRLEN], dst_buf[INET6_ADDRSTRLEN];
+	struct ipv6hdr *pkt = (struct ipv6hdr *)packet;
+	const char *src, *dst;
+	u_char proto;
+
+	src = inet_ntop(AF_INET6, &pkt->saddr, src_buf, sizeof(src_buf));
+	if (!src)
+		src = "<invalid>";
+	dst = inet_ntop(AF_INET6, &pkt->daddr, dst_buf, sizeof(dst_buf));
+	if (!dst)
+		dst = "<invalid>";
+	proto = pkt->nexthdr;
+	show_transport(packet + sizeof(struct ipv6hdr),
+		       ntohs(pkt->payload_len),
+		       ifindex, src, dst, proto, true, pkt_type);
+}
+
+static void show_ipv4_packet(const u_char *packet, u32 ifindex, u8 pkt_type)
+{
+	char src_buf[INET_ADDRSTRLEN], dst_buf[INET_ADDRSTRLEN];
+	struct iphdr *pkt = (struct iphdr *)packet;
+	const char *src, *dst;
+	u_char proto;
+
+	src = inet_ntop(AF_INET, &pkt->saddr, src_buf, sizeof(src_buf));
+	if (!src)
+		src = "<invalid>";
+	dst = inet_ntop(AF_INET, &pkt->daddr, dst_buf, sizeof(dst_buf));
+	if (!dst)
+		dst = "<invalid>";
+	proto = pkt->protocol;
+	show_transport(packet + sizeof(struct iphdr),
+		       ntohs(pkt->tot_len),
+		       ifindex, src, dst, proto, false, pkt_type);
+}
+
+static void *traffic_monitor_thread(void *arg)
+{
+	char *ifname, _ifname[IF_NAMESIZE];
+	const u_char *packet, *payload;
+	struct tmonitor_ctx *ctx = arg;
+	pcap_dumper_t *dumper = ctx->dumper;
+	int fd = ctx->pcap_fd, nfds, r;
+	int wake_fd = ctx->wake_fd;
+	struct pcap_pkthdr header;
+	pcap_t *pcap = ctx->pcap;
+	u32 ifindex;
+	fd_set fds;
+	u16 proto;
+	u8 ptype;
+
+	nfds = (fd > wake_fd ? fd : wake_fd) + 1;
+	FD_ZERO(&fds);
+
+	while (!ctx->done) {
+		FD_SET(fd, &fds);
+		FD_SET(wake_fd, &fds);
+		r = select(nfds, &fds, NULL, NULL, NULL);
+		if (!r)
+			continue;
+		if (r < 0) {
+			if (errno == EINTR)
+				continue;
+			log_err("Fail to select on pcap fd and wake fd");
+			break;
+		}
+
+		/* This instance of pcap is non-blocking */
+		packet = pcap_next(pcap, &header);
+		if (!packet)
+			continue;
+
+		/* According to the man page of pcap_dump(), first argument
+		 * is the pcap_dumper_t pointer even it's argument type is
+		 * u_char *.
+		 */
+		pcap_dump((u_char *)dumper, &header, packet);
+
+		/* Not sure what other types of packets look like. Here, we
+		 * parse only Ethernet and compatible packets.
+		 */
+		if (!is_ethernet(packet))
+			continue;
+
+		/* Skip SLL2 header
+		 * https://www.tcpdump.org/linktypes/LINKTYPE_LINUX_SLL2.html
+		 *
+		 * Although the document doesn't mention that, the payload
+		 * doesn't include the Ethernet header. The payload starts
+		 * from the first byte of the network layer header.
+		 */
+		payload = packet + 20;
+
+		memcpy(&proto, packet, 2);
+		proto = ntohs(proto);
+		memcpy(&ifindex, packet + 4, 4);
+		ifindex = ntohl(ifindex);
+		ptype = packet[10];
+
+		if (proto == ETH_P_IPV6) {
+			show_ipv6_packet(payload, ifindex, ptype);
+		} else if (proto == ETH_P_IP) {
+			show_ipv4_packet(payload, ifindex, ptype);
+		} else {
+			ifname = if_indextoname(ifindex, _ifname);
+			if (!ifname) {
+				snprintf(_ifname, sizeof(_ifname), "unknown(%d)", ifindex);
+				ifname = _ifname;
+			}
+
+			printf("%-7s %-3s Unknown network protocol type 0x%x\n",
+			       ifname, pkt_type_str(ptype), proto);
+		}
+	}
+
+	return NULL;
+}
+
+/* Prepare the pcap handle to capture packets.
+ *
+ * This pcap is non-blocking and immediate mode is enabled to receive
+ * captured packets as soon as possible.  The snaplen is set to 1024 bytes
+ * to limit the size of captured content. The format of the link-layer
+ * header is set to DLT_LINUX_SLL2 to enable handling various link-layer
+ * technologies.
+ */
+static pcap_t *traffic_monitor_prepare_pcap(void)
+{
+	char errbuf[PCAP_ERRBUF_SIZE];
+	pcap_t *pcap;
+	int r;
+
+	/* Listen on all NICs in the namespace */
+	pcap = pcap_create("any", errbuf);
+	if (!pcap) {
+		log_err("Failed to open pcap: %s", errbuf);
+		return NULL;
+	}
+	/* Limit the size of the packet (first N bytes) */
+	r = pcap_set_snaplen(pcap, 1024);
+	if (r) {
+		log_err("Failed to set snaplen: %s", pcap_geterr(pcap));
+		goto error;
+	}
+	/* To receive packets as fast as possible */
+	r = pcap_set_immediate_mode(pcap, 1);
+	if (r) {
+		log_err("Failed to set immediate mode: %s", pcap_geterr(pcap));
+		goto error;
+	}
+	r = pcap_setnonblock(pcap, 1, errbuf);
+	if (r) {
+		log_err("Failed to set nonblock: %s", errbuf);
+		goto error;
+	}
+	r = pcap_activate(pcap);
+	if (r) {
+		log_err("Failed to activate pcap: %s", pcap_geterr(pcap));
+		goto error;
+	}
+	/* Determine the format of the link-layer header */
+	r = pcap_set_datalink(pcap, DLT_LINUX_SLL2);
+	if (r) {
+		log_err("Failed to set datalink: %s", pcap_geterr(pcap));
+		goto error;
+	}
+
+	return pcap;
+error:
+	pcap_close(pcap);
+	return NULL;
+}
+
+static void encode_test_name(char *buf, size_t len, const char *test_name, const char *subtest_name)
+{
+	char *p;
+
+	if (subtest_name)
+		snprintf(buf, len, "%s__%s", test_name, subtest_name);
+	else
+		snprintf(buf, len, "%s", test_name);
+	while ((p = strchr(buf, '/')))
+		*p = '_';
+	while ((p = strchr(buf, ' ')))
+		*p = '_';
+}
+
+#define PCAP_DIR "/tmp/tmon_pcap"
+
+/* Start to monitor the network traffic in the given network namespace.
+ *
+ * netns: the name of the network namespace to monitor. If NULL, the
+ *        current network namespace is monitored.
+ * test_name: the name of the running test.
+ * subtest_name: the name of the running subtest if there is. It should be
+ *               NULL if it is not a subtest.
+ *
+ * This function will start a thread to capture packets going through NICs
+ * in the give network namespace.
+ */
+struct tmonitor_ctx *traffic_monitor_start(const char *netns, const char *test_name,
+					   const char *subtest_name)
+{
+	struct nstoken *nstoken = NULL;
+	struct tmonitor_ctx *ctx;
+	char test_name_buf[64];
+	static int tmon_seq;
+	int r;
+
+	if (netns) {
+		nstoken = open_netns(netns);
+		if (!nstoken)
+			return NULL;
+	}
+	ctx = malloc(sizeof(*ctx));
+	if (!ctx) {
+		log_err("Failed to malloc ctx");
+		goto fail_ctx;
+	}
+	memset(ctx, 0, sizeof(*ctx));
+
+	encode_test_name(test_name_buf, sizeof(test_name_buf), test_name, subtest_name);
+	snprintf(ctx->pkt_fname, sizeof(ctx->pkt_fname),
+		 PCAP_DIR "/packets-%d-%d-%s-%s.log", getpid(), tmon_seq++,
+		 test_name_buf, netns ? netns : "unknown");
+
+	r = mkdir(PCAP_DIR, 0755);
+	if (r && errno != EEXIST) {
+		log_err("Failed to create " PCAP_DIR);
+		goto fail_pcap;
+	}
+
+	ctx->pcap = traffic_monitor_prepare_pcap();
+	if (!ctx->pcap)
+		goto fail_pcap;
+	ctx->pcap_fd = pcap_get_selectable_fd(ctx->pcap);
+	if (ctx->pcap_fd < 0) {
+		log_err("Failed to get pcap fd");
+		goto fail_dumper;
+	}
+
+	/* Create a packet file */
+	ctx->dumper = pcap_dump_open(ctx->pcap, ctx->pkt_fname);
+	if (!ctx->dumper) {
+		log_err("Failed to open pcap dump: %s", ctx->pkt_fname);
+		goto fail_dumper;
+	}
+
+	/* Create an eventfd to wake up the monitor thread */
+	ctx->wake_fd = eventfd(0, 0);
+	if (ctx->wake_fd < 0) {
+		log_err("Failed to create eventfd");
+		goto fail_eventfd;
+	}
+
+	r = pthread_create(&ctx->thread, NULL, traffic_monitor_thread, ctx);
+	if (r) {
+		log_err("Failed to create thread");
+		goto fail;
+	}
+
+	close_netns(nstoken);
+
+	return ctx;
+
+fail:
+	close(ctx->wake_fd);
+
+fail_eventfd:
+	pcap_dump_close(ctx->dumper);
+	unlink(ctx->pkt_fname);
+
+fail_dumper:
+	pcap_close(ctx->pcap);
+
+fail_pcap:
+	free(ctx);
+
+fail_ctx:
+	close_netns(nstoken);
+
+	return NULL;
+}
+
+static void traffic_monitor_release(struct tmonitor_ctx *ctx)
+{
+	pcap_close(ctx->pcap);
+	pcap_dump_close(ctx->dumper);
+
+	close(ctx->wake_fd);
+
+	free(ctx);
+}
+
+/* Stop the network traffic monitor.
+ *
+ * ctx: the context returned by traffic_monitor_start()
+ */
+void traffic_monitor_stop(struct tmonitor_ctx *ctx)
+{
+	__u64 w = 1;
+
+	if (!ctx)
+		return;
+
+	/* Stop the monitor thread */
+	ctx->done = true;
+	/* Wake up the background thread. */
+	write(ctx->wake_fd, &w, sizeof(w));
+	pthread_join(ctx->thread, NULL);
+
+	printf("Packet file: %s\n", strrchr(ctx->pkt_fname, '/') + 1);
+
+	traffic_monitor_release(ctx);
+}
+#endif /* TRAFFIC_MONITOR */
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index aac5b94d6379..c72c16e1aff8 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -23,7 +23,6 @@ typedef __u16 __sum16;
 
 struct network_helper_opts {
 	int timeout_ms;
-	bool must_fail;
 	int proto;
 	/* +ve: Passed to listen() as-is.
 	 *   0: Default when the test does not set
@@ -70,8 +69,10 @@ int client_socket(int family, int type,
 		  const struct network_helper_opts *opts);
 int connect_to_addr(int type, const struct sockaddr_storage *addr, socklen_t len,
 		    const struct network_helper_opts *opts);
+int connect_to_addr_str(int family, int type, const char *addr_str, __u16 port,
+			const struct network_helper_opts *opts);
 int connect_to_fd(int server_fd, int timeout_ms);
-int connect_to_fd_opts(int server_fd, int type, const struct network_helper_opts *opts);
+int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts);
 int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms);
 int fastopen_connect(int server_fd, const char *data, unsigned int data_len,
 		     int timeout_ms);
@@ -92,6 +93,8 @@ struct nstoken;
 struct nstoken *open_netns(const char *name);
 void close_netns(struct nstoken *token);
 int send_recv_data(int lfd, int fd, uint32_t total_bytes);
+int make_netns(const char *name);
+int remove_netns(const char *name);
 
 static __u16 csum_fold(__u32 csum)
 {
@@ -135,4 +138,22 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 	return csum_fold((__u32)s);
 }
 
+struct tmonitor_ctx;
+
+#ifdef TRAFFIC_MONITOR
+struct tmonitor_ctx *traffic_monitor_start(const char *netns, const char *test_name,
+					   const char *subtest_name);
+void traffic_monitor_stop(struct tmonitor_ctx *ctx);
+#else
+static inline struct tmonitor_ctx *traffic_monitor_start(const char *netns, const char *test_name,
+							 const char *subtest_name)
+{
+	return NULL;
+}
+
+static inline void traffic_monitor_stop(struct tmonitor_ctx *ctx)
+{
+}
+#endif
+
 #endif
diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index 7175af39134f..329c7862b52d 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -283,9 +283,11 @@ static void test_uprobe_sleepable(struct test_attach_probe *skel)
 	trigger_func3();
 
 	ASSERT_EQ(skel->bss->uprobe_byname3_sleepable_res, 9, "check_uprobe_byname3_sleepable_res");
-	ASSERT_EQ(skel->bss->uprobe_byname3_res, 10, "check_uprobe_byname3_res");
-	ASSERT_EQ(skel->bss->uretprobe_byname3_sleepable_res, 11, "check_uretprobe_byname3_sleepable_res");
-	ASSERT_EQ(skel->bss->uretprobe_byname3_res, 12, "check_uretprobe_byname3_res");
+	ASSERT_EQ(skel->bss->uprobe_byname3_str_sleepable_res, 10, "check_uprobe_byname3_str_sleepable_res");
+	ASSERT_EQ(skel->bss->uprobe_byname3_res, 11, "check_uprobe_byname3_res");
+	ASSERT_EQ(skel->bss->uretprobe_byname3_sleepable_res, 12, "check_uretprobe_byname3_sleepable_res");
+	ASSERT_EQ(skel->bss->uretprobe_byname3_str_sleepable_res, 13, "check_uretprobe_byname3_str_sleepable_res");
+	ASSERT_EQ(skel->bss->uretprobe_byname3_res, 14, "check_uretprobe_byname3_res");
 }
 
 void test_attach_probe(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 618af9dfae9b..52e6f7570475 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -1218,7 +1218,7 @@ out:
 	bpf_iter_bpf_sk_storage_helpers__destroy(skel);
 }
 
-static void test_bpf_sk_stoarge_map_iter_fd(void)
+static void test_bpf_sk_storage_map_iter_fd(void)
 {
 	struct bpf_iter_bpf_sk_storage_map *skel;
 
@@ -1693,7 +1693,7 @@ void test_bpf_iter(void)
 	if (test__start_subtest("bpf_sk_storage_map"))
 		test_bpf_sk_storage_map();
 	if (test__start_subtest("bpf_sk_storage_map_iter_fd"))
-		test_bpf_sk_stoarge_map_iter_fd();
+		test_bpf_sk_storage_map_iter_fd();
 	if (test__start_subtest("bpf_sk_storage_delete"))
 		test_bpf_sk_storage_delete();
 	if (test__start_subtest("bpf_sk_storage_get"))
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c
index b52ff8ce34db..16bed9dd8e6a 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c
@@ -95,7 +95,7 @@ static unsigned short get_local_port(int fd)
 	struct sockaddr_in6 addr;
 	socklen_t addrlen = sizeof(addr);
 
-	if (!getsockname(fd, &addr, &addrlen))
+	if (!getsockname(fd, (struct sockaddr *)&addr, &addrlen))
 		return ntohs(addr.sin6_port);
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index 63422f4f3896..409a06975823 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -49,7 +49,7 @@ static bool start_test(char *addr_str,
 		goto err;
 
 	/* connect to server */
-	*cli_fd = connect_to_fd_opts(*srv_fd, SOCK_STREAM, cli_opts);
+	*cli_fd = connect_to_fd_opts(*srv_fd, cli_opts);
 	if (!ASSERT_NEQ(*cli_fd, -1, "connect_to_fd_opts"))
 		goto err;
 
@@ -285,7 +285,7 @@ static void test_dctcp_fallback(void)
 	dctcp_skel = bpf_dctcp__open();
 	if (!ASSERT_OK_PTR(dctcp_skel, "dctcp_skel"))
 		return;
-	strcpy(dctcp_skel->rodata->fallback, "cubic");
+	strcpy(dctcp_skel->rodata->fallback_cc, "cubic");
 	if (!ASSERT_OK(bpf_dctcp__load(dctcp_skel), "bpf_dctcp__load"))
 		goto done;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 61de88cf4ad0..e63d74ce046f 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -5020,7 +5020,7 @@ struct pprint_mapv_int128 {
 static struct btf_raw_test pprint_test_template[] = {
 {
 	.raw_types = {
-		/* unsighed char */			/* [1] */
+		/* unsigned char */			/* [1] */
 		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
 		/* unsigned short */			/* [2] */
 		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 16, 2),
@@ -5087,7 +5087,7 @@ static struct btf_raw_test pprint_test_template[] = {
 	 * be encoded with kind_flag set.
 	 */
 	.raw_types = {
-		/* unsighed char */			/* [1] */
+		/* unsigned char */			/* [1] */
 		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
 		/* unsigned short */			/* [2] */
 		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 16, 2),
@@ -5154,7 +5154,7 @@ static struct btf_raw_test pprint_test_template[] = {
 	 * will have both int and enum types.
 	 */
 	.raw_types = {
-		/* unsighed char */			/* [1] */
+		/* unsigned char */			/* [1] */
 		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
 		/* unsigned short */			/* [2] */
 		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 16, 2),
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_distill.c b/tools/testing/selftests/bpf/prog_tests/btf_distill.c
index bfbe795823a2..ca84726d5ac1 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_distill.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_distill.c
@@ -535,6 +535,72 @@ cleanup:
 	btf__free(vmlinux_btf);
 }
 
+/* Split and new base BTFs should inherit endianness from source BTF. */
+static void test_distilled_endianness(void)
+{
+	struct btf *base = NULL, *split = NULL, *new_base = NULL, *new_split = NULL;
+	struct btf *new_base1 = NULL, *new_split1 = NULL;
+	enum btf_endianness inverse_endianness;
+	const void *raw_data;
+	__u32 size;
+
+	base = btf__new_empty();
+	if (!ASSERT_OK_PTR(base, "empty_main_btf"))
+		return;
+	inverse_endianness = btf__endianness(base) == BTF_LITTLE_ENDIAN ? BTF_BIG_ENDIAN
+									: BTF_LITTLE_ENDIAN;
+	btf__set_endianness(base, inverse_endianness);
+	btf__add_int(base, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	VALIDATE_RAW_BTF(
+		base,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED");
+	split = btf__new_empty_split(base);
+	if (!ASSERT_OK_PTR(split, "empty_split_btf"))
+		goto cleanup;
+	btf__add_ptr(split, 1);
+	VALIDATE_RAW_BTF(
+		split,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1");
+	if (!ASSERT_EQ(0, btf__distill_base(split, &new_base, &new_split),
+		       "distilled_base") ||
+	    !ASSERT_OK_PTR(new_base, "distilled_base") ||
+	    !ASSERT_OK_PTR(new_split, "distilled_split") ||
+	    !ASSERT_EQ(2, btf__type_cnt(new_base), "distilled_base_type_cnt"))
+		goto cleanup;
+	VALIDATE_RAW_BTF(
+		new_split,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1");
+
+	raw_data = btf__raw_data(new_base, &size);
+	if (!ASSERT_OK_PTR(raw_data, "btf__raw_data #1"))
+		goto cleanup;
+	new_base1 = btf__new(raw_data, size);
+	if (!ASSERT_OK_PTR(new_base1, "new_base1 = btf__new()"))
+		goto cleanup;
+	raw_data = btf__raw_data(new_split, &size);
+	if (!ASSERT_OK_PTR(raw_data, "btf__raw_data #2"))
+		goto cleanup;
+	new_split1 = btf__new_split(raw_data, size, new_base1);
+	if (!ASSERT_OK_PTR(new_split1, "new_split1 = btf__new()"))
+		goto cleanup;
+
+	ASSERT_EQ(btf__endianness(new_base1), inverse_endianness, "new_base1 endianness");
+	ASSERT_EQ(btf__endianness(new_split1), inverse_endianness, "new_split1 endianness");
+	VALIDATE_RAW_BTF(
+		new_split1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1");
+cleanup:
+	btf__free(new_split1);
+	btf__free(new_base1);
+	btf__free(new_split);
+	btf__free(new_base);
+	btf__free(split);
+	btf__free(base);
+}
+
 void test_btf_distill(void)
 {
 	if (test__start_subtest("distilled_base"))
@@ -549,4 +615,6 @@ void test_btf_distill(void)
 		test_distilled_base_multi_err2();
 	if (test__start_subtest("distilled_base_vmlinux"))
 		test_distilled_base_vmlinux();
+	if (test__start_subtest("distilled_endianness"))
+		test_distilled_endianness();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index 09a8e6f9b379..b293b8501fd6 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -805,8 +805,8 @@ static void test_btf_dump_var_data(struct btf *btf, struct btf_dump *d,
 	TEST_BTF_DUMP_VAR(btf, d, NULL, str, "cpu_number", int, BTF_F_COMPACT,
 			  "int cpu_number = (int)100", 100);
 #endif
-	TEST_BTF_DUMP_VAR(btf, d, NULL, str, "cpu_profile_flip", int, BTF_F_COMPACT,
-			  "static int cpu_profile_flip = (int)2", 2);
+	TEST_BTF_DUMP_VAR(btf, d, NULL, str, "bpf_cgrp_storage_busy", int, BTF_F_COMPACT,
+			  "static int bpf_cgrp_storage_busy = (int)2", 2);
 }
 
 static void test_btf_datasec(struct btf *btf, struct btf_dump *d, char *str,
diff --git a/tools/testing/selftests/bpf/prog_tests/build_id.c b/tools/testing/selftests/bpf/prog_tests/build_id.c
new file mode 100644
index 000000000000..aec9c8d6bc96
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/build_id.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+
+#include "test_build_id.skel.h"
+
+static char build_id[BPF_BUILD_ID_SIZE];
+static int build_id_sz;
+
+static void print_stack(struct bpf_stack_build_id *stack, int frame_cnt)
+{
+	int i, j;
+
+	for (i = 0; i < frame_cnt; i++) {
+		printf("FRAME #%02d: ", i);
+		switch (stack[i].status) {
+		case BPF_STACK_BUILD_ID_EMPTY:
+			printf("<EMPTY>\n");
+			break;
+		case BPF_STACK_BUILD_ID_VALID:
+			printf("BUILD ID = ");
+			for (j = 0; j < BPF_BUILD_ID_SIZE; j++)
+				printf("%02hhx", (unsigned)stack[i].build_id[j]);
+			printf(" OFFSET = %llx", (unsigned long long)stack[i].offset);
+			break;
+		case BPF_STACK_BUILD_ID_IP:
+			printf("IP = %llx", (unsigned long long)stack[i].ip);
+			break;
+		default:
+			printf("UNEXPECTED STATUS %d ", stack[i].status);
+			break;
+		}
+		printf("\n");
+	}
+}
+
+static void subtest_nofault(bool build_id_resident)
+{
+	struct test_build_id *skel;
+	struct bpf_stack_build_id *stack;
+	int frame_cnt;
+
+	skel = test_build_id__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->links.uprobe_nofault = bpf_program__attach(skel->progs.uprobe_nofault);
+	if (!ASSERT_OK_PTR(skel->links.uprobe_nofault, "link"))
+		goto cleanup;
+
+	if (build_id_resident)
+		ASSERT_OK(system("./uprobe_multi uprobe-paged-in"), "trigger_uprobe");
+	else
+		ASSERT_OK(system("./uprobe_multi uprobe-paged-out"), "trigger_uprobe");
+
+	if (!ASSERT_GT(skel->bss->res_nofault, 0, "res"))
+		goto cleanup;
+
+	stack = skel->bss->stack_nofault;
+	frame_cnt = skel->bss->res_nofault / sizeof(struct bpf_stack_build_id);
+	if (env.verbosity >= VERBOSE_NORMAL)
+		print_stack(stack, frame_cnt);
+
+	if (build_id_resident) {
+		ASSERT_EQ(stack[0].status, BPF_STACK_BUILD_ID_VALID, "build_id_status");
+		ASSERT_EQ(memcmp(stack[0].build_id, build_id, build_id_sz), 0, "build_id_match");
+	} else {
+		ASSERT_EQ(stack[0].status, BPF_STACK_BUILD_ID_IP, "build_id_status");
+	}
+
+cleanup:
+	test_build_id__destroy(skel);
+}
+
+static void subtest_sleepable(void)
+{
+	struct test_build_id *skel;
+	struct bpf_stack_build_id *stack;
+	int frame_cnt;
+
+	skel = test_build_id__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->links.uprobe_sleepable = bpf_program__attach(skel->progs.uprobe_sleepable);
+	if (!ASSERT_OK_PTR(skel->links.uprobe_sleepable, "link"))
+		goto cleanup;
+
+	/* force build ID to not be paged in */
+	ASSERT_OK(system("./uprobe_multi uprobe-paged-out"), "trigger_uprobe");
+
+	if (!ASSERT_GT(skel->bss->res_sleepable, 0, "res"))
+		goto cleanup;
+
+	stack = skel->bss->stack_sleepable;
+	frame_cnt = skel->bss->res_sleepable / sizeof(struct bpf_stack_build_id);
+	if (env.verbosity >= VERBOSE_NORMAL)
+		print_stack(stack, frame_cnt);
+
+	ASSERT_EQ(stack[0].status, BPF_STACK_BUILD_ID_VALID, "build_id_status");
+	ASSERT_EQ(memcmp(stack[0].build_id, build_id, build_id_sz), 0, "build_id_match");
+
+cleanup:
+	test_build_id__destroy(skel);
+}
+
+void serial_test_build_id(void)
+{
+	build_id_sz = read_build_id("uprobe_multi", build_id, sizeof(build_id));
+	ASSERT_EQ(build_id_sz, BPF_BUILD_ID_SIZE, "parse_build_id");
+
+	if (test__start_subtest("nofault-paged-out"))
+		subtest_nofault(false /* not resident */);
+	if (test__start_subtest("nofault-paged-in"))
+		subtest_nofault(true /* resident */);
+	if (test__start_subtest("sleepable"))
+		subtest_sleepable();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
index 63ee892bc757..10224f845568 100644
--- a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
@@ -214,7 +214,7 @@ static void test_isolated(int parent_cgroup_fd, int child_cgroup_fd)
 	/* Attach to parent and child cgroup, trigger packet from child.
 	 * Assert that there is six additional runs, parent cgroup egresses and
 	 * ingress, child cgroup egresses and ingress.
-	 * Assert that egree and ingress storages are separate.
+	 * Assert that egress and ingress storages are separate.
 	 */
 	child_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1,
 							child_cgroup_fd);
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_ancestor.c b/tools/testing/selftests/bpf/prog_tests/cgroup_ancestor.c
new file mode 100644
index 000000000000..9250a1e9f9af
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_ancestor.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "cgroup_helpers.h"
+#include "cgroup_ancestor.skel.h"
+
+#define CGROUP_PATH "/skb_cgroup_test"
+#define TEST_NS "cgroup_ancestor_ns"
+#define NUM_CGROUP_LEVELS 4
+#define WAIT_AUTO_IP_MAX_ATTEMPT 10
+#define DST_ADDR "::1"
+#define DST_PORT 1234
+#define MAX_ASSERT_NAME 32
+
+struct test_data {
+	struct cgroup_ancestor *skel;
+	struct bpf_tc_hook qdisc;
+	struct bpf_tc_opts tc_attach;
+	struct nstoken *ns;
+};
+
+static int send_datagram(void)
+{
+	unsigned char buf[] = "some random test data";
+	struct sockaddr_in6 addr = { .sin6_family = AF_INET6,
+				     .sin6_port = htons(DST_PORT), };
+	int sock, n;
+
+	if (!ASSERT_EQ(inet_pton(AF_INET6, DST_ADDR, &addr.sin6_addr), 1,
+		       "inet_pton"))
+		return -1;
+
+	sock = socket(AF_INET6, SOCK_DGRAM, 0);
+	if (!ASSERT_OK_FD(sock, "create socket"))
+		return sock;
+
+	if (!ASSERT_OK(connect(sock, &addr, sizeof(addr)), "connect")) {
+		close(sock);
+		return -1;
+	}
+
+	n = sendto(sock, buf, sizeof(buf), 0, (const struct sockaddr *)&addr,
+		   sizeof(addr));
+	close(sock);
+	return ASSERT_EQ(n, sizeof(buf), "send data") ? 0 : -1;
+}
+
+static int setup_network(struct test_data *t)
+{
+	SYS(fail, "ip netns add %s", TEST_NS);
+	t->ns = open_netns(TEST_NS);
+	if (!ASSERT_OK_PTR(t->ns, "open netns"))
+		goto cleanup_ns;
+
+	SYS(close_ns, "ip link set lo up");
+
+	memset(&t->qdisc, 0, sizeof(t->qdisc));
+	t->qdisc.sz = sizeof(t->qdisc);
+	t->qdisc.attach_point = BPF_TC_EGRESS;
+	t->qdisc.ifindex = if_nametoindex("lo");
+	if (!ASSERT_NEQ(t->qdisc.ifindex, 0, "if_nametoindex"))
+		goto close_ns;
+	if (!ASSERT_OK(bpf_tc_hook_create(&t->qdisc), "qdisc add"))
+		goto close_ns;
+
+	memset(&t->tc_attach, 0, sizeof(t->tc_attach));
+	t->tc_attach.sz = sizeof(t->tc_attach);
+	t->tc_attach.prog_fd = bpf_program__fd(t->skel->progs.log_cgroup_id);
+	if (!ASSERT_OK(bpf_tc_attach(&t->qdisc, &t->tc_attach), "filter add"))
+		goto cleanup_qdisc;
+
+	return 0;
+
+cleanup_qdisc:
+	bpf_tc_hook_destroy(&t->qdisc);
+close_ns:
+	close_netns(t->ns);
+cleanup_ns:
+	SYS_NOFAIL("ip netns del %s", TEST_NS);
+fail:
+	return 1;
+}
+
+static void cleanup_network(struct test_data *t)
+{
+	bpf_tc_detach(&t->qdisc, &t->tc_attach);
+	bpf_tc_hook_destroy(&t->qdisc);
+	close_netns(t->ns);
+	SYS_NOFAIL("ip netns del %s", TEST_NS);
+}
+
+static void check_ancestors_ids(struct test_data *t)
+{
+	__u64 expected_ids[NUM_CGROUP_LEVELS];
+	char assert_name[MAX_ASSERT_NAME];
+	__u32 level;
+
+	expected_ids[0] = get_cgroup_id("/.."); /* root cgroup */
+	expected_ids[1] = get_cgroup_id("");
+	expected_ids[2] = get_cgroup_id(CGROUP_PATH);
+	expected_ids[3] = 0; /* non-existent cgroup */
+
+	for (level = 0; level < NUM_CGROUP_LEVELS; level++) {
+		snprintf(assert_name, MAX_ASSERT_NAME,
+			 "ancestor id at level %d", level);
+		ASSERT_EQ(t->skel->bss->cgroup_ids[level], expected_ids[level],
+			  assert_name);
+	}
+}
+
+void test_cgroup_ancestor(void)
+{
+	struct test_data t;
+	int cgroup_fd;
+
+	t.skel = cgroup_ancestor__open_and_load();
+	if (!ASSERT_OK_PTR(t.skel, "open and load"))
+		return;
+
+	t.skel->bss->dport = htons(DST_PORT);
+	cgroup_fd = cgroup_setup_and_join(CGROUP_PATH);
+	if (cgroup_fd < 0)
+		goto cleanup_progs;
+
+	if (setup_network(&t))
+		goto cleanup_cgroups;
+
+	if (send_datagram())
+		goto cleanup_network;
+
+	check_ancestors_ids(&t);
+
+cleanup_network:
+	cleanup_network(&t);
+cleanup_cgroups:
+	close(cgroup_fd);
+	cleanup_cgroup_environment();
+cleanup_progs:
+	cgroup_ancestor__destroy(t.skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_dev.c b/tools/testing/selftests/bpf/prog_tests/cgroup_dev.c
new file mode 100644
index 000000000000..5ab7547e38c0
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_dev.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <sys/stat.h>
+#include <sys/sysmacros.h>
+#include <errno.h>
+#include "test_progs.h"
+#include "cgroup_helpers.h"
+#include "dev_cgroup.skel.h"
+
+#define TEST_CGROUP "/test-bpf-based-device-cgroup/"
+#define TEST_BUFFER_SIZE 64
+
+static void test_mknod(const char *path, mode_t mode, int dev_major,
+		       int dev_minor, int expected_ret, int expected_errno)
+{
+	int ret;
+
+	unlink(path);
+	ret = mknod(path, mode, makedev(dev_major, dev_minor));
+	ASSERT_EQ(ret, expected_ret, "mknod");
+	if (expected_ret)
+		ASSERT_EQ(errno, expected_errno, "mknod errno");
+	else
+		unlink(path);
+}
+
+static void test_read(const char *path, char *buf, int buf_size,
+		      int expected_ret, int expected_errno)
+{
+	int ret, fd;
+
+	fd = open(path, O_RDONLY);
+
+	/* A bare open on unauthorized device should fail */
+	if (expected_ret < 0) {
+		ASSERT_EQ(fd, expected_ret, "open ret for read");
+		ASSERT_EQ(errno, expected_errno, "open errno for read");
+		if (fd >= 0)
+			close(fd);
+		return;
+	}
+
+	if (!ASSERT_OK_FD(fd, "open ret for read"))
+		return;
+
+	ret = read(fd, buf, buf_size);
+	ASSERT_EQ(ret, expected_ret, "read");
+
+	close(fd);
+}
+
+static void test_write(const char *path, char *buf, int buf_size,
+		       int expected_ret, int expected_errno)
+{
+	int ret, fd;
+
+	fd = open(path, O_WRONLY);
+
+	/* A bare open on unauthorized device should fail */
+	if (expected_ret < 0) {
+		ASSERT_EQ(fd, expected_ret, "open ret for write");
+		ASSERT_EQ(errno, expected_errno, "open errno for write");
+		if (fd >= 0)
+			close(fd);
+		return;
+	}
+
+	if (!ASSERT_OK_FD(fd, "open ret for write"))
+		return;
+
+	ret = write(fd, buf, buf_size);
+	ASSERT_EQ(ret, expected_ret, "write");
+
+	close(fd);
+}
+
+void test_cgroup_dev(void)
+{
+	char buf[TEST_BUFFER_SIZE] = "some random test data";
+	struct dev_cgroup *skel;
+	int cgroup_fd;
+
+	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
+	if (!ASSERT_OK_FD(cgroup_fd, "cgroup switch"))
+		return;
+
+	skel = dev_cgroup__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "load program"))
+		goto cleanup_cgroup;
+
+	skel->links.bpf_prog1 =
+		bpf_program__attach_cgroup(skel->progs.bpf_prog1, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.bpf_prog1, "attach_program"))
+		goto cleanup_progs;
+
+	if (test__start_subtest("allow-mknod"))
+		test_mknod("/dev/test_dev_cgroup_null", S_IFCHR, 1, 3, 0, 0);
+
+	if (test__start_subtest("allow-read"))
+		test_read("/dev/urandom", buf, TEST_BUFFER_SIZE,
+			  TEST_BUFFER_SIZE, 0);
+
+	if (test__start_subtest("allow-write"))
+		test_write("/dev/null", buf, TEST_BUFFER_SIZE,
+			   TEST_BUFFER_SIZE, 0);
+
+	if (test__start_subtest("deny-mknod"))
+		test_mknod("/dev/test_dev_cgroup_zero", S_IFCHR, 1, 5, -1,
+			   EPERM);
+
+	if (test__start_subtest("deny-read"))
+		test_read("/dev/random", buf, TEST_BUFFER_SIZE, -1, EPERM);
+
+	if (test__start_subtest("deny-write"))
+		test_write("/dev/zero", buf, TEST_BUFFER_SIZE, -1, EPERM);
+
+	if (test__start_subtest("deny-mknod-wrong-type"))
+		test_mknod("/dev/test_dev_cgroup_block", S_IFBLK, 1, 3, -1,
+			   EPERM);
+
+cleanup_progs:
+	dev_cgroup__destroy(skel);
+cleanup_cgroup:
+	cleanup_cgroup_environment();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_get_current_cgroup_id.c b/tools/testing/selftests/bpf/prog_tests/cgroup_get_current_cgroup_id.c
new file mode 100644
index 000000000000..7a1643b03bf3
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_get_current_cgroup_id.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <sys/stat.h>
+#include <sys/sysmacros.h>
+#include "test_progs.h"
+#include "cgroup_helpers.h"
+#include "get_cgroup_id_kern.skel.h"
+
+#define TEST_CGROUP "/test-bpf-get-cgroup-id/"
+
+void test_cgroup_get_current_cgroup_id(void)
+{
+	struct get_cgroup_id_kern *skel;
+	const struct timespec req = {
+		.tv_sec = 0,
+		.tv_nsec = 1,
+	};
+	int cgroup_fd;
+	__u64 ucgid;
+
+	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
+	if (!ASSERT_OK_FD(cgroup_fd, "cgroup switch"))
+		return;
+
+	skel = get_cgroup_id_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "load program"))
+		goto cleanup_cgroup;
+
+	if (!ASSERT_OK(get_cgroup_id_kern__attach(skel), "attach bpf program"))
+		goto cleanup_progs;
+
+	skel->bss->expected_pid = getpid();
+	/* trigger the syscall on which is attached the tested prog */
+	if (!ASSERT_OK(syscall(__NR_nanosleep, &req, NULL), "nanosleep"))
+		goto cleanup_progs;
+
+	ucgid = get_cgroup_id(TEST_CGROUP);
+
+	ASSERT_EQ(skel->bss->cg_id, ucgid, "compare cgroup ids");
+
+cleanup_progs:
+	get_cgroup_id_kern__destroy(skel);
+cleanup_cgroup:
+	close(cgroup_fd);
+	cleanup_cgroup_environment();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_storage.c b/tools/testing/selftests/bpf/prog_tests/cgroup_storage.c
new file mode 100644
index 000000000000..cf395715ced4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_storage.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "network_helpers.h"
+#include "cgroup_storage.skel.h"
+
+#define TEST_CGROUP "/test-bpf-cgroup-storage-buf/"
+#define TEST_NS "cgroup_storage_ns"
+#define PING_CMD "ping localhost -c 1 -W 1 -q"
+
+static int setup_network(struct nstoken **token)
+{
+	SYS(fail, "ip netns add %s", TEST_NS);
+	*token = open_netns(TEST_NS);
+	if (!ASSERT_OK_PTR(*token, "open netns"))
+		goto cleanup_ns;
+	SYS(cleanup_ns, "ip link set lo up");
+
+	return 0;
+
+cleanup_ns:
+	SYS_NOFAIL("ip netns del %s", TEST_NS);
+fail:
+	return -1;
+}
+
+static void cleanup_network(struct nstoken *ns)
+{
+	close_netns(ns);
+	SYS_NOFAIL("ip netns del %s", TEST_NS);
+}
+
+void test_cgroup_storage(void)
+{
+	struct bpf_cgroup_storage_key key;
+	struct cgroup_storage *skel;
+	struct nstoken *ns = NULL;
+	unsigned long long value;
+	int cgroup_fd;
+	int err;
+
+	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
+	if (!ASSERT_OK_FD(cgroup_fd, "create cgroup"))
+		return;
+
+	if (!ASSERT_OK(setup_network(&ns), "setup network"))
+		goto cleanup_cgroup;
+
+	skel = cgroup_storage__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "load program"))
+		goto cleanup_network;
+
+	skel->links.bpf_prog =
+		bpf_program__attach_cgroup(skel->progs.bpf_prog, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.bpf_prog, "attach program"))
+		goto cleanup_progs;
+
+	/* Check that one out of every two packets is dropped */
+	err = SYS_NOFAIL(PING_CMD);
+	ASSERT_OK(err, "first ping");
+	err = SYS_NOFAIL(PING_CMD);
+	ASSERT_NEQ(err, 0, "second ping");
+	err = SYS_NOFAIL(PING_CMD);
+	ASSERT_OK(err, "third ping");
+
+	err = bpf_map__get_next_key(skel->maps.cgroup_storage, NULL, &key,
+				    sizeof(key));
+	if (!ASSERT_OK(err, "get first key"))
+		goto cleanup_progs;
+	err = bpf_map__lookup_elem(skel->maps.cgroup_storage, &key, sizeof(key),
+				   &value, sizeof(value), 0);
+	if (!ASSERT_OK(err, "first packet count read"))
+		goto cleanup_progs;
+
+	/* Add one to the packet counter, check again packet filtering */
+	value++;
+	err = bpf_map__update_elem(skel->maps.cgroup_storage, &key, sizeof(key),
+				   &value, sizeof(value), 0);
+	if (!ASSERT_OK(err, "increment packet counter"))
+		goto cleanup_progs;
+	err = SYS_NOFAIL(PING_CMD);
+	ASSERT_OK(err, "fourth ping");
+	err = SYS_NOFAIL(PING_CMD);
+	ASSERT_NEQ(err, 0, "fifth ping");
+	err = SYS_NOFAIL(PING_CMD);
+	ASSERT_OK(err, "sixth ping");
+
+cleanup_progs:
+	cgroup_storage__destroy(skel);
+cleanup_network:
+	cleanup_network(ns);
+cleanup_cgroup:
+	close(cgroup_fd);
+	cleanup_cgroup_environment();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
index 9709c8db7275..64abba72ac10 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
@@ -9,9 +9,6 @@
 
 static int run_test(int cgroup_fd, int server_fd, bool classid)
 {
-	struct network_helper_opts opts = {
-		.must_fail = true,
-	};
 	struct connect4_dropper *skel;
 	int fd, err = 0;
 
@@ -32,11 +29,16 @@ static int run_test(int cgroup_fd, int server_fd, bool classid)
 		goto out;
 	}
 
-	fd = connect_to_fd_opts(server_fd, SOCK_STREAM, &opts);
-	if (fd < 0)
+	errno = 0;
+	fd = connect_to_fd_opts(server_fd, NULL);
+	if (fd >= 0) {
+		log_err("Unexpected success to connect to server");
 		err = -1;
-	else
 		close(fd);
+	} else if (errno != EPERM) {
+		log_err("Unexpected errno from connect to server");
+		err = -1;
+	}
 out:
 	connect4_dropper__destroy(skel);
 	return err;
@@ -52,7 +54,7 @@ void test_cgroup_v1v2(void)
 	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0);
 	if (!ASSERT_GE(server_fd, 0, "server_fd"))
 		return;
-	client_fd = connect_to_fd_opts(server_fd, SOCK_STREAM, &opts);
+	client_fd = connect_to_fd_opts(server_fd, &opts);
 	if (!ASSERT_GE(client_fd, 0, "client_fd")) {
 		close(server_fd);
 		return;
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 47f42e680105..26019313e1fc 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
 #include <test_progs.h>
 #include "progs/core_reloc_types.h"
 #include "bpf_testmod/bpf_testmod.h"
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc_raw.c b/tools/testing/selftests/bpf/prog_tests/core_reloc_raw.c
new file mode 100644
index 000000000000..a18d3680fb16
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc_raw.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Test cases that can't load programs using libbpf and need direct
+ * BPF syscall access
+ */
+
+#include <sys/syscall.h>
+#include <bpf/libbpf.h>
+#include <bpf/btf.h>
+
+#include "test_progs.h"
+#include "test_btf.h"
+#include "bpf/libbpf_internal.h"
+
+static char log[16 * 1024];
+
+/* Check that verifier rejects BPF program containing relocation
+ * pointing to non-existent BTF type.
+ */
+static void test_bad_local_id(void)
+{
+	struct test_btf {
+		struct btf_header hdr;
+		__u32 types[15];
+		char strings[128];
+	} raw_btf = {
+		.hdr = {
+			.magic = BTF_MAGIC,
+			.version = BTF_VERSION,
+			.hdr_len = sizeof(struct btf_header),
+			.type_off = 0,
+			.type_len = sizeof(raw_btf.types),
+			.str_off = offsetof(struct test_btf, strings) -
+				   offsetof(struct test_btf, types),
+			.str_len = sizeof(raw_btf.strings),
+		},
+		.types = {
+			BTF_PTR_ENC(0),					/* [1] void*  */
+			BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),	/* [2] int    */
+			BTF_FUNC_PROTO_ENC(2, 1),			/* [3] int (*)(void*) */
+			BTF_FUNC_PROTO_ARG_ENC(8, 1),
+			BTF_FUNC_ENC(8, 3)			/* [4] FUNC 'foo' type_id=2   */
+		},
+		.strings = "\0int\0 0\0foo\0"
+	};
+	__u32 log_level = 1 | 2 | 4;
+	LIBBPF_OPTS(bpf_btf_load_opts, opts,
+		    .log_buf = log,
+		    .log_size = sizeof(log),
+		    .log_level = log_level,
+	);
+	struct bpf_insn insns[] = {
+		BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	struct bpf_func_info funcs[] = {
+		{
+			.insn_off = 0,
+			.type_id = 4,
+		}
+	};
+	struct bpf_core_relo relos[] = {
+		{
+			.insn_off = 0,		/* patch first instruction (r0 = 0) */
+			.type_id = 100500,	/* !!! this type id does not exist */
+			.access_str_off = 6,	/* offset of "0" */
+			.kind = BPF_CORE_TYPE_ID_LOCAL,
+		}
+	};
+	union bpf_attr attr;
+	int saved_errno;
+	int prog_fd = -1;
+	int btf_fd = -1;
+
+	btf_fd = bpf_btf_load(&raw_btf, sizeof(raw_btf), &opts);
+	saved_errno = errno;
+	if (btf_fd < 0 || env.verbosity > VERBOSE_NORMAL) {
+		printf("-------- BTF load log start --------\n");
+		printf("%s", log);
+		printf("-------- BTF load log end ----------\n");
+	}
+	if (btf_fd < 0) {
+		PRINT_FAIL("bpf_btf_load() failed, errno=%d\n", saved_errno);
+		return;
+	}
+
+	log[0] = 0;
+	memset(&attr, 0, sizeof(attr));
+	attr.prog_btf_fd = btf_fd;
+	attr.prog_type = BPF_TRACE_RAW_TP;
+	attr.license = (__u64)"GPL";
+	attr.insns = (__u64)&insns;
+	attr.insn_cnt = sizeof(insns) / sizeof(*insns);
+	attr.log_buf = (__u64)log;
+	attr.log_size = sizeof(log);
+	attr.log_level = log_level;
+	attr.func_info = (__u64)funcs;
+	attr.func_info_cnt = sizeof(funcs) / sizeof(*funcs);
+	attr.func_info_rec_size = sizeof(*funcs);
+	attr.core_relos = (__u64)relos;
+	attr.core_relo_cnt = sizeof(relos) / sizeof(*relos);
+	attr.core_relo_rec_size = sizeof(*relos);
+	prog_fd = sys_bpf_prog_load(&attr, sizeof(attr), 1);
+	saved_errno = errno;
+	if (prog_fd < 0 || env.verbosity > VERBOSE_NORMAL) {
+		printf("-------- program load log start --------\n");
+		printf("%s", log);
+		printf("-------- program load log end ----------\n");
+	}
+	if (prog_fd >= 0) {
+		PRINT_FAIL("sys_bpf_prog_load() expected to fail\n");
+		goto out;
+	}
+	ASSERT_HAS_SUBSTR(log, "relo #0: bad type id 100500", "program load log");
+
+out:
+	close(prog_fd);
+	close(btf_fd);
+}
+
+void test_core_reloc_raw(void)
+{
+	if (test__start_subtest("bad_local_id"))
+		test_bad_local_id();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/crypto_sanity.c b/tools/testing/selftests/bpf/prog_tests/crypto_sanity.c
index b1a3a49a822a..42bd07f7218d 100644
--- a/tools/testing/selftests/bpf/prog_tests/crypto_sanity.c
+++ b/tools/testing/selftests/bpf/prog_tests/crypto_sanity.c
@@ -4,7 +4,6 @@
 #include <sys/types.h>
 #include <sys/socket.h>
 #include <net/if.h>
-#include <linux/in6.h>
 #include <linux/if_alg.h>
 
 #include "test_progs.h"
diff --git a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
index 08b6391f2f56..dd75ccb03770 100644
--- a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
+++ b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
@@ -10,7 +10,8 @@
 #include "bpf/btf.h"
 #include "bpf_util.h"
 #include "linux/filter.h"
-#include "disasm.h"
+#include "linux/kernel.h"
+#include "disasm_helpers.h"
 
 #define MAX_PROG_TEXT_SZ (32 * 1024)
 
@@ -628,63 +629,6 @@ err:
 	return false;
 }
 
-static void print_insn(void *private_data, const char *fmt, ...)
-{
-	va_list args;
-
-	va_start(args, fmt);
-	vfprintf((FILE *)private_data, fmt, args);
-	va_end(args);
-}
-
-/* Disassemble instructions to a stream */
-static void print_xlated(FILE *out, struct bpf_insn *insn, __u32 len)
-{
-	const struct bpf_insn_cbs cbs = {
-		.cb_print	= print_insn,
-		.cb_call	= NULL,
-		.cb_imm		= NULL,
-		.private_data	= out,
-	};
-	bool double_insn = false;
-	int i;
-
-	for (i = 0; i < len; i++) {
-		if (double_insn) {
-			double_insn = false;
-			continue;
-		}
-
-		double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW);
-		print_bpf_insn(&cbs, insn + i, true);
-	}
-}
-
-/* We share code with kernel BPF disassembler, it adds '(FF) ' prefix
- * for each instruction (FF stands for instruction `code` byte).
- * This function removes the prefix inplace for each line in `str`.
- */
-static void remove_insn_prefix(char *str, int size)
-{
-	const int prefix_size = 5;
-
-	int write_pos = 0, read_pos = prefix_size;
-	int len = strlen(str);
-	char c;
-
-	size = min(size, len);
-
-	while (read_pos < size) {
-		c = str[read_pos++];
-		if (c == 0)
-			break;
-		str[write_pos++] = c;
-		if (c == '\n')
-			read_pos += prefix_size;
-	}
-	str[write_pos] = 0;
-}
-
 struct prog_info {
 	char *prog_kind;
 	enum bpf_prog_type prog_type;
@@ -699,9 +643,10 @@ static void match_program(struct btf *btf,
 			  char *reg_map[][2],
 			  bool skip_first_insn)
 {
-	struct bpf_insn *buf = NULL;
+	struct bpf_insn *buf = NULL, *insn, *insn_end;
 	int err = 0, prog_fd = 0;
 	FILE *prog_out = NULL;
+	char insn_buf[64];
 	char *text = NULL;
 	__u32 cnt = 0;
 
@@ -739,12 +684,13 @@ static void match_program(struct btf *btf,
 		PRINT_FAIL("Can't open memory stream\n");
 		goto out;
 	}
-	if (skip_first_insn)
-		print_xlated(prog_out, buf + 1, cnt - 1);
-	else
-		print_xlated(prog_out, buf, cnt);
+	insn_end = buf + cnt;
+	insn = buf + (skip_first_insn ? 1 : 0);
+	while (insn < insn_end) {
+		insn = disasm_insn(insn, insn_buf, sizeof(insn_buf));
+		fprintf(prog_out, "%s\n", insn_buf);
+	}
 	fclose(prog_out);
-	remove_insn_prefix(text, MAX_PROG_TEXT_SZ);
 
 	ASSERT_TRUE(match_pattern(btf, pattern, text, reg_map),
 		    pinfo->prog_kind);
diff --git a/tools/testing/selftests/bpf/prog_tests/decap_sanity.c b/tools/testing/selftests/bpf/prog_tests/decap_sanity.c
index dcb9e5070cc3..d79f398ec6b7 100644
--- a/tools/testing/selftests/bpf/prog_tests/decap_sanity.c
+++ b/tools/testing/selftests/bpf/prog_tests/decap_sanity.c
@@ -4,7 +4,6 @@
 #include <sys/types.h>
 #include <sys/socket.h>
 #include <net/if.h>
-#include <linux/in6.h>
 
 #include "test_progs.h"
 #include "network_helpers.h"
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c
index 49b1ffc9af1f..14c91b6f1e83 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
+#include "bpf_util.h"
 
 void serial_test_fexit_stress(void)
 {
@@ -36,7 +37,7 @@ void serial_test_fexit_stress(void)
 	for (i = 0; i < bpf_max_tramp_links; i++) {
 		fexit_fd[i] = bpf_prog_load(BPF_PROG_TYPE_TRACING, NULL, "GPL",
 					    trace_program,
-					    sizeof(trace_program) / sizeof(struct bpf_insn),
+					    ARRAY_SIZE(trace_program),
 					    &trace_opts);
 		if (!ASSERT_GE(fexit_fd[i], 0, "fexit load"))
 			goto out;
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index 6b3078dd5645..cfcc90cb7ffb 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
 #include <test_progs.h>
 #include <network_helpers.h>
-#include <error.h>
 #include <linux/if_tun.h>
 #include <sys/uio.h>
 
diff --git a/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c b/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c
index 37056ba73847..5a0b51157451 100644
--- a/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c
+++ b/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c
@@ -16,6 +16,7 @@ static void test_xattr(void)
 {
 	struct test_get_xattr *skel = NULL;
 	int fd = -1, err;
+	int v[32];
 
 	fd = open(testfile, O_CREAT | O_RDONLY, 0644);
 	if (!ASSERT_GE(fd, 0, "create_file"))
@@ -50,7 +51,13 @@ static void test_xattr(void)
 	if (!ASSERT_GE(fd, 0, "open_file"))
 		goto out;
 
-	ASSERT_EQ(skel->bss->found_xattr, 1, "found_xattr");
+	ASSERT_EQ(skel->bss->found_xattr_from_file, 1, "found_xattr_from_file");
+
+	/* Trigger security_inode_getxattr */
+	err = getxattr(testfile, "user.kfuncs", v, sizeof(v));
+	ASSERT_EQ(err, -1, "getxattr_return");
+	ASSERT_EQ(errno, EINVAL, "getxattr_errno");
+	ASSERT_EQ(skel->bss->found_xattr_from_dentry, 1, "found_xattr_from_dentry");
 
 out:
 	close(fd);
diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c
index 3c440370c1f0..89ff23c4a8bc 100644
--- a/tools/testing/selftests/bpf/prog_tests/iters.c
+++ b/tools/testing/selftests/bpf/prog_tests/iters.c
@@ -14,6 +14,7 @@
 #include "iters_state_safety.skel.h"
 #include "iters_looping.skel.h"
 #include "iters_num.skel.h"
+#include "iters_testmod.skel.h"
 #include "iters_testmod_seq.skel.h"
 #include "iters_task_vma.skel.h"
 #include "iters_task.skel.h"
@@ -297,8 +298,10 @@ void test_iters(void)
 	RUN_TESTS(iters);
 	RUN_TESTS(iters_css_task);
 
-	if (env.has_testmod)
+	if (env.has_testmod) {
+		RUN_TESTS(iters_testmod);
 		RUN_TESTS(iters_testmod_seq);
+	}
 
 	if (test__start_subtest("num"))
 		subtest_num_iters();
diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
index c07991544a78..34f8822fd221 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
 #include <test_progs.h>
 #include <network_helpers.h>
 #include "kfree_skb.skel.h"
diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
index 5b743212292f..f79c8e53cb3e 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
@@ -68,6 +68,7 @@ static struct kfunc_test_params kfunc_tests[] = {
 	TC_FAIL(kfunc_call_test_get_mem_fail_oob, 0, "min value is outside of the allowed memory range"),
 	TC_FAIL(kfunc_call_test_get_mem_fail_not_const, 0, "is not a const"),
 	TC_FAIL(kfunc_call_test_mem_acquire_fail, 0, "acquire kernel function does not return PTR_TO_BTF_ID"),
+	TC_FAIL(kfunc_call_test_pointer_arg_type_mismatch, 0, "arg#0 expected pointer to ctx, but got scalar"),
 
 	/* success cases */
 	TC_TEST(kfunc_call_test1, 12),
diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c
index 0f7ea4d7d9f6..27676a04d0b6 100644
--- a/tools/testing/selftests/bpf/prog_tests/log_buf.c
+++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c
@@ -5,6 +5,7 @@
 #include <bpf/btf.h>
 
 #include "test_log_buf.skel.h"
+#include "bpf_util.h"
 
 static size_t libbpf_log_pos;
 static char libbpf_log_buf[1024 * 1024];
@@ -143,11 +144,11 @@ static void bpf_prog_load_log_buf(void)
 		BPF_MOV64_IMM(BPF_REG_0, 0),
 		BPF_EXIT_INSN(),
 	};
-	const size_t good_prog_insn_cnt = sizeof(good_prog_insns) / sizeof(struct bpf_insn);
+	const size_t good_prog_insn_cnt = ARRAY_SIZE(good_prog_insns);
 	const struct bpf_insn bad_prog_insns[] = {
 		BPF_EXIT_INSN(),
 	};
-	size_t bad_prog_insn_cnt = sizeof(bad_prog_insns) / sizeof(struct bpf_insn);
+	size_t bad_prog_insn_cnt = ARRAY_SIZE(bad_prog_insns);
 	LIBBPF_OPTS(bpf_prog_load_opts, opts);
 	const size_t log_buf_sz = 1024 * 1024;
 	char *log_buf;
@@ -159,7 +160,7 @@ static void bpf_prog_load_log_buf(void)
 	opts.log_buf = log_buf;
 	opts.log_size = log_buf_sz;
 
-	/* with log_level == 0 log_buf shoud stay empty for good prog */
+	/* with log_level == 0 log_buf should stay empty for good prog */
 	log_buf[0] = '\0';
 	opts.log_level = 0;
 	fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "good_prog", "GPL",
@@ -221,7 +222,7 @@ static void bpf_btf_load_log_buf(void)
 	opts.log_buf = log_buf;
 	opts.log_size = log_buf_sz;
 
-	/* with log_level == 0 log_buf shoud stay empty for good BTF */
+	/* with log_level == 0 log_buf should stay empty for good BTF */
 	log_buf[0] = '\0';
 	opts.log_level = 0;
 	fd = bpf_btf_load(raw_btf_data, raw_btf_size, &opts);
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c b/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c
index 835a1d756c16..b6e8d822e8e9 100644
--- a/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c
@@ -47,7 +47,6 @@
 #include <linux/if_ether.h>
 #include <linux/if_packet.h>
 #include <linux/if_tun.h>
-#include <linux/icmp.h>
 #include <arpa/inet.h>
 #include <unistd.h>
 #include <errno.h>
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c b/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c
index 03825d2b45a8..6c50c0f63f43 100644
--- a/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c
@@ -49,6 +49,7 @@
  *  is not crashed, it is considered successful.
  */
 #define NETNS "ns_lwt_reroute"
+#include <netinet/in.h>
 #include "lwt_helpers.h"
 #include "network_helpers.h"
 #include <linux/net_tstamp.h>
diff --git a/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c b/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c
index aa9f67eb1c95..bea05f78de5f 100644
--- a/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c
+++ b/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c
@@ -4,6 +4,7 @@
 #include <bpf/btf.h>
 #include "bpf/libbpf_internal.h"
 #include "cgroup_helpers.h"
+#include "bpf_util.h"
 
 static const char *module_name = "bpf_testmod";
 static const char *symbol_name = "bpf_fentry_shadow_test";
@@ -100,7 +101,7 @@ void test_module_fentry_shadow(void)
 		load_opts.attach_btf_obj_fd = btf_fd[i];
 		prog_fd[i] = bpf_prog_load(BPF_PROG_TYPE_TRACING, NULL, "GPL",
 					   trace_program,
-					   sizeof(trace_program) / sizeof(struct bpf_insn),
+					   ARRAY_SIZE(trace_program),
 					   &load_opts);
 		if (!ASSERT_GE(prog_fd[i], 0, "bpf_prog_load"))
 			goto out;
diff --git a/tools/testing/selftests/bpf/prog_tests/nested_trust.c b/tools/testing/selftests/bpf/prog_tests/nested_trust.c
index 39886f58924e..54a112ad5f9c 100644
--- a/tools/testing/selftests/bpf/prog_tests/nested_trust.c
+++ b/tools/testing/selftests/bpf/prog_tests/nested_trust.c
@@ -4,9 +4,13 @@
 #include <test_progs.h>
 #include "nested_trust_failure.skel.h"
 #include "nested_trust_success.skel.h"
+#include "nested_acquire.skel.h"
 
 void test_nested_trust(void)
 {
 	RUN_TESTS(nested_trust_success);
 	RUN_TESTS(nested_trust_failure);
+
+	if (env.has_testmod)
+		RUN_TESTS(nested_acquire);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
index e72d75d6baa7..c29787e092d6 100644
--- a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
+++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
@@ -11,7 +11,7 @@
 #include <sched.h>
 #include <sys/wait.h>
 #include <sys/mount.h>
-#include <sys/fcntl.h>
+#include <fcntl.h>
 #include "network_helpers.h"
 
 #define STACK_SIZE (1024 * 1024)
diff --git a/tools/testing/selftests/bpf/prog_tests/parse_tcp_hdr_opt.c b/tools/testing/selftests/bpf/prog_tests/parse_tcp_hdr_opt.c
index daa952711d8f..e9c07d561ded 100644
--- a/tools/testing/selftests/bpf/prog_tests/parse_tcp_hdr_opt.c
+++ b/tools/testing/selftests/bpf/prog_tests/parse_tcp_hdr_opt.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
+#define _GNU_SOURCE
 #include <test_progs.h>
 #include <network_helpers.h>
 #include "test_parse_tcp_hdr_opt.skel.h"
diff --git a/tools/testing/selftests/bpf/prog_tests/pro_epilogue.c b/tools/testing/selftests/bpf/prog_tests/pro_epilogue.c
new file mode 100644
index 000000000000..509883e6823a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/pro_epilogue.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include "pro_epilogue.skel.h"
+#include "epilogue_tailcall.skel.h"
+#include "pro_epilogue_goto_start.skel.h"
+#include "epilogue_exit.skel.h"
+
+struct st_ops_args {
+	__u64 a;
+};
+
+static void test_tailcall(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct epilogue_tailcall *skel;
+	struct st_ops_args args;
+	int err, prog_fd;
+
+	skel = epilogue_tailcall__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "epilogue_tailcall__open_and_load"))
+		return;
+
+	topts.ctx_in = &args;
+	topts.ctx_size_in = sizeof(args);
+
+	skel->links.epilogue_tailcall =
+		bpf_map__attach_struct_ops(skel->maps.epilogue_tailcall);
+	if (!ASSERT_OK_PTR(skel->links.epilogue_tailcall, "attach_struct_ops"))
+		goto done;
+
+	/* Both test_epilogue_tailcall and test_epilogue_subprog are
+	 * patched with epilogue. When syscall_epilogue_tailcall()
+	 * is run, test_epilogue_tailcall() is triggered.
+	 * It executes a tail call and control is transferred to
+	 * test_epilogue_subprog(). Only test_epilogue_subprog()
+	 * does args->a += 1, thus final args.a value of 10001
+	 * guarantees that only the epilogue of the
+	 * test_epilogue_subprog is executed.
+	 */
+	memset(&args, 0, sizeof(args));
+	prog_fd = bpf_program__fd(skel->progs.syscall_epilogue_tailcall);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+	ASSERT_EQ(args.a, 10001, "args.a");
+	ASSERT_EQ(topts.retval, 10001 * 2, "topts.retval");
+
+done:
+	epilogue_tailcall__destroy(skel);
+}
+
+void test_pro_epilogue(void)
+{
+	RUN_TESTS(pro_epilogue);
+	RUN_TESTS(pro_epilogue_goto_start);
+	RUN_TESTS(epilogue_exit);
+	if (test__start_subtest("tailcall"))
+		test_tailcall();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c
index e2f1445b0e10..216b0dfac0fe 100644
--- a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c
+++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c
@@ -2,6 +2,7 @@
 
 #include <test_progs.h>
 #include <linux/nbd.h>
+#include "bpf_util.h"
 
 void test_raw_tp_writable_reject_nbd_invalid(void)
 {
@@ -25,7 +26,7 @@ void test_raw_tp_writable_reject_nbd_invalid(void)
 	);
 
 	bpf_fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, NULL, "GPL v2",
-			       program, sizeof(program) / sizeof(struct bpf_insn),
+			       program, ARRAY_SIZE(program),
 			       &opts);
 	if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable load",
 		  "failed: %d errno %d\n", bpf_fd, errno))
diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c
index f4aa7dab4766..e3668058b7bb 100644
--- a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c
+++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c
@@ -2,6 +2,7 @@
 
 #include <test_progs.h>
 #include <linux/nbd.h>
+#include "bpf_util.h"
 
 /* NOTE: conflict with other tests. */
 void serial_test_raw_tp_writable_test_run(void)
@@ -24,7 +25,7 @@ void serial_test_raw_tp_writable_test_run(void)
 	);
 
 	int bpf_fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, NULL, "GPL v2",
-				   trace_program, sizeof(trace_program) / sizeof(struct bpf_insn),
+				   trace_program, ARRAY_SIZE(trace_program),
 				   &trace_opts);
 	if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable loaded",
 		  "failed: %d errno %d\n", bpf_fd, errno))
@@ -41,7 +42,7 @@ void serial_test_raw_tp_writable_test_run(void)
 	);
 
 	int filter_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL v2",
-				      skb_program, sizeof(skb_program) / sizeof(struct bpf_insn),
+				      skb_program, ARRAY_SIZE(skb_program),
 				      &skb_opts);
 	if (CHECK(filter_fd < 0, "test_program_loaded", "failed: %d errno %d\n",
 		  filter_fd, errno))
diff --git a/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c
index 3405923fe4e6..c7b9ba8b1d06 100644
--- a/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c
@@ -23,6 +23,7 @@ struct read_ret_desc {
 	{ .name = "probe_read_user_str", .ret = -EFAULT },
 	{ .name = "copy_from_user", .ret = -EFAULT },
 	{ .name = "copy_from_user_task", .ret = -EFAULT },
+	{ .name = "copy_from_user_str", .ret = -EFAULT },
 };
 
 void test_read_vsyscall(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
index eb74363f9f70..39d42271cc46 100644
--- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
+++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
@@ -433,6 +433,19 @@ static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t,
 
 	y_cast = range_cast(y_t, x_t, y);
 
+	/* If we know that
+	 *   - *x* is in the range of signed 32bit value, and
+	 *   - *y_cast* range is 32-bit signed non-negative
+	 * then *x* range can be improved with *y_cast* such that *x* range
+	 * is 32-bit signed non-negative. Otherwise, if the new range for *x*
+	 * allows upper 32-bit * 0xffffffff then the eventual new range for
+	 * *x* will be out of signed 32-bit range which violates the origin
+	 * *x* range.
+	 */
+	if (x_t == S64 && y_t == S32 && y_cast.a <= S32_MAX  && y_cast.b <= S32_MAX &&
+	    (s64)x.a >= S32_MIN && (s64)x.b <= S32_MAX)
+		return range_improve(x_t, x, y_cast);
+
 	/* the case when new range knowledge, *y*, is a 32-bit subregister
 	 * range, while previous range knowledge, *x*, is a full register
 	 * 64-bit range, needs special treatment to take into account upper 32
@@ -490,7 +503,7 @@ static const char *op_str(enum op op)
 
 /* Can register with range [x.a, x.b] *EVER* satisfy
  * OP (<, <=, >, >=, ==, !=) relation to
- * a regsiter with range [y.a, y.b]
+ * a register with range [y.a, y.b]
  * _in *num_t* domain_
  */
 static bool range_canbe_op(enum num_t t, struct range x, struct range y, enum op op)
@@ -519,7 +532,7 @@ static bool range_canbe_op(enum num_t t, struct range x, struct range y, enum op
 
 /* Does register with range [x.a, x.b] *ALWAYS* satisfy
  * OP (<, <=, >, >=, ==, !=) relation to
- * a regsiter with range [y.a, y.b]
+ * a register with range [y.a, y.b]
  * _in *num_t* domain_
  */
 static bool range_always_op(enum num_t t, struct range x, struct range y, enum op op)
@@ -530,7 +543,7 @@ static bool range_always_op(enum num_t t, struct range x, struct range y, enum o
 
 /* Does register with range [x.a, x.b] *NEVER* satisfy
  * OP (<, <=, >, >=, ==, !=) relation to
- * a regsiter with range [y.a, y.b]
+ * a register with range [y.a, y.b]
  * _in *num_t* domain_
  */
 static bool range_never_op(enum num_t t, struct range x, struct range y, enum op op)
@@ -1005,11 +1018,11 @@ static int parse_reg_state(const char *s, struct reg_state *reg)
 	 *     - umin=%llu, if missing, assumed 0;
 	 *     - umax=%llu, if missing, assumed U64_MAX;
 	 *     - smin=%lld, if missing, assumed S64_MIN;
-	 *     - smax=%lld, if missing, assummed S64_MAX;
+	 *     - smax=%lld, if missing, assumed S64_MAX;
 	 *     - umin32=%d, if missing, assumed 0;
 	 *     - umax32=%d, if missing, assumed U32_MAX;
 	 *     - smin32=%d, if missing, assumed S32_MIN;
-	 *     - smax32=%d, if missing, assummed S32_MAX;
+	 *     - smax32=%d, if missing, assumed S32_MAX;
 	 *     - var_off=(%#llx; %#llx), tnum part, we don't care about it.
 	 *
 	 * If some of the values are equal, they will be grouped (but min/max
@@ -1474,7 +1487,7 @@ static int verify_case_opt(struct ctx *ctx, enum num_t init_t, enum num_t cond_t
 			u64 elapsed_ns = get_time_ns() - ctx->start_ns;
 			double remain_ns = elapsed_ns / progress * (1 - progress);
 
-			fprintf(env.stderr, "PROGRESS (%s): %d/%d (%.2lf%%), "
+			fprintf(env.stderr_saved, "PROGRESS (%s): %d/%d (%.2lf%%), "
 					    "elapsed %llu mins (%.2lf hrs), "
 					    "ETA %.0lf mins (%.2lf hrs)\n",
 				ctx->progress_ctx,
@@ -1871,7 +1884,7 @@ cleanup:
  * envvar is not set, this test is skipped during test_progs testing.
  *
  * We split this up into smaller subsets based on initialization and
- * conditiona numeric domains to get an easy parallelization with test_progs'
+ * conditional numeric domains to get an easy parallelization with test_progs'
  * -j argument.
  */
 
@@ -1925,7 +1938,7 @@ static u64 rand_u64()
 {
 	/* RAND_MAX is guaranteed to be at least 1<<15, but in practice it
 	 * seems to be 1<<31, so we need to call it thrice to get full u64;
-	 * we'll use rougly equal split: 22 + 21 + 21 bits
+	 * we'll use roughly equal split: 22 + 21 + 21 bits
 	 */
 	return ((u64)random() << 42) |
 	       (((u64)random() & RAND_21BIT_MASK) << 21) |
@@ -2108,6 +2121,9 @@ static struct subtest_case crafted_cases[] = {
 	{S32, U32, {(u32)S32_MIN, 0}, {0, 0}},
 	{S32, U32, {(u32)S32_MIN, 0}, {(u32)S32_MIN, (u32)S32_MIN}},
 	{S32, U32, {(u32)S32_MIN, S32_MAX}, {S32_MAX, S32_MAX}},
+	{S64, U32, {0x0, 0x1f}, {0xffffffff80000000ULL, 0x000000007fffffffULL}},
+	{S64, U32, {0x0, 0x1f}, {0xffffffffffff8000ULL, 0x0000000000007fffULL}},
+	{S64, U32, {0x0, 0x1f}, {0xffffffffffffff80ULL, 0x000000000000007fULL}},
 };
 
 /* Go over crafted hard-coded cases. This is fast, so we do it as part of
diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
index f81d08d429a2..51544372f52e 100644
--- a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
+++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
@@ -103,7 +103,7 @@ static int resolve_symbols(void)
 
 	btf = btf__parse_elf("btf_data.bpf.o", NULL);
 	if (CHECK(libbpf_get_error(btf), "resolve",
-		  "Failed to load BTF from btf_data.o\n"))
+		  "Failed to load BTF from btf_data.bpf.o\n"))
 		return -1;
 
 	nr = btf__type_cnt(btf);
diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
index 64c5f5eb2994..036d4760d2c1 100644
--- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
+++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
@@ -37,9 +37,7 @@ static int sk_fds[REUSEPORT_ARRAY_SIZE];
 static int reuseport_array = -1, outer_map = -1;
 static enum bpf_map_type inner_map_type;
 static int select_by_skb_data_prog;
-static int saved_tcp_syncookie = -1;
 static struct bpf_object *obj;
-static int saved_tcp_fo = -1;
 static __u32 index_zero;
 static int epfd;
 
@@ -193,14 +191,6 @@ static int write_int_sysctl(const char *sysctl, int v)
 	return 0;
 }
 
-static void restore_sysctls(void)
-{
-	if (saved_tcp_fo != -1)
-		write_int_sysctl(TCP_FO_SYSCTL, saved_tcp_fo);
-	if (saved_tcp_syncookie != -1)
-		write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, saved_tcp_syncookie);
-}
-
 static int enable_fastopen(void)
 {
 	int fo;
@@ -793,6 +783,7 @@ static void test_config(int sotype, sa_family_t family, bool inany)
 		TEST_INIT(test_pass_on_err),
 		TEST_INIT(test_detach_bpf),
 	};
+	struct netns_obj *netns;
 	char s[MAX_TEST_NAME];
 	const struct test *t;
 
@@ -808,9 +799,21 @@ static void test_config(int sotype, sa_family_t family, bool inany)
 		if (!test__start_subtest(s))
 			continue;
 
+		netns = netns_new("select_reuseport", true);
+		if (!ASSERT_OK_PTR(netns, "netns_new"))
+			continue;
+
+		if (CHECK_FAIL(enable_fastopen()))
+			goto out;
+		if (CHECK_FAIL(disable_syncookie()))
+			goto out;
+
 		setup_per_test(sotype, family, inany, t->no_inner_map);
 		t->fn(sotype, family);
 		cleanup_per_test(t->no_inner_map);
+
+out:
+		netns_free(netns);
 	}
 }
 
@@ -850,21 +853,7 @@ out:
 
 void serial_test_select_reuseport(void)
 {
-	saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL);
-	if (saved_tcp_fo < 0)
-		goto out;
-	saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL);
-	if (saved_tcp_syncookie < 0)
-		goto out;
-
-	if (enable_fastopen())
-		goto out;
-	if (disable_syncookie())
-		goto out;
-
 	test_map_type(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY);
 	test_map_type(BPF_MAP_TYPE_SOCKMAP);
 	test_map_type(BPF_MAP_TYPE_SOCKHASH);
-out:
-	restore_sysctls();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
index ae87c00867ba..023c31bde229 100644
--- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
@@ -18,7 +18,6 @@
 #include <arpa/inet.h>
 #include <assert.h>
 #include <errno.h>
-#include <error.h>
 #include <fcntl.h>
 #include <sched.h>
 #include <stdio.h>
@@ -47,8 +46,6 @@
 #define INT_IP6		"fd00::2"
 #define INT_PORT	8008
 
-#define IO_TIMEOUT_SEC	3
-
 enum server {
 	SERVER_A = 0,
 	SERVER_B = 1,
@@ -108,46 +105,6 @@ static int attach_reuseport(int sock_fd, struct bpf_program *reuseport_prog)
 	return 0;
 }
 
-static socklen_t inetaddr_len(const struct sockaddr_storage *addr)
-{
-	return (addr->ss_family == AF_INET ? sizeof(struct sockaddr_in) :
-		addr->ss_family == AF_INET6 ? sizeof(struct sockaddr_in6) : 0);
-}
-
-static int make_socket(int sotype, const char *ip, int port,
-		       struct sockaddr_storage *addr)
-{
-	struct timeval timeo = { .tv_sec = IO_TIMEOUT_SEC };
-	int err, family, fd;
-
-	family = is_ipv6(ip) ? AF_INET6 : AF_INET;
-	err = make_sockaddr(family, ip, port, addr, NULL);
-	if (CHECK(err, "make_address", "failed\n"))
-		return -1;
-
-	fd = socket(addr->ss_family, sotype, 0);
-	if (CHECK(fd < 0, "socket", "failed\n")) {
-		log_err("failed to make socket");
-		return -1;
-	}
-
-	err = setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeo, sizeof(timeo));
-	if (CHECK(err, "setsockopt(SO_SNDTIMEO)", "failed\n")) {
-		log_err("failed to set SNDTIMEO");
-		close(fd);
-		return -1;
-	}
-
-	err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeo, sizeof(timeo));
-	if (CHECK(err, "setsockopt(SO_RCVTIMEO)", "failed\n")) {
-		log_err("failed to set RCVTIMEO");
-		close(fd);
-		return -1;
-	}
-
-	return fd;
-}
-
 static int setsockopts(int fd, void *opts)
 {
 	struct cb_opts *co = (struct cb_opts *)opts;
@@ -229,27 +186,6 @@ fail:
 	return -1;
 }
 
-static int make_client(int sotype, const char *ip, int port)
-{
-	struct sockaddr_storage addr = {0};
-	int err, fd;
-
-	fd = make_socket(sotype, ip, port, &addr);
-	if (fd < 0)
-		return -1;
-
-	err = connect(fd, (void *)&addr, inetaddr_len(&addr));
-	if (CHECK(err, "make_client", "connect")) {
-		log_err("failed to connect client socket");
-		goto fail;
-	}
-
-	return fd;
-fail:
-	close(fd);
-	return -1;
-}
-
 static __u64 socket_cookie(int fd)
 {
 	__u64 cookie;
@@ -646,8 +582,9 @@ static void run_lookup_prog(const struct test *t)
 			goto close;
 	}
 
-	client_fd = make_client(t->sotype, t->connect_to.ip, t->connect_to.port);
-	if (client_fd < 0)
+	client_fd = connect_to_addr_str(is_ipv6(t->connect_to.ip) ? AF_INET6 : AF_INET,
+					t->sotype, t->connect_to.ip, t->connect_to.port, NULL);
+	if (!ASSERT_OK_FD(client_fd, "connect_to_addr_str"))
 		goto close;
 
 	if (t->sotype == SOCK_STREAM)
@@ -862,9 +799,11 @@ static void test_redirect_lookup(struct test_sk_lookup *skel)
 
 static void drop_on_lookup(const struct test *t)
 {
+	int family = is_ipv6(t->connect_to.ip) ? AF_INET6 : AF_INET;
 	struct sockaddr_storage dst = {};
 	int client_fd, server_fd, err;
 	struct bpf_link *lookup_link;
+	socklen_t len;
 	ssize_t n;
 
 	lookup_link = attach_lookup_prog(t->lookup_prog);
@@ -876,12 +815,14 @@ static void drop_on_lookup(const struct test *t)
 	if (server_fd < 0)
 		goto detach;
 
-	client_fd = make_socket(t->sotype, t->connect_to.ip,
-				t->connect_to.port, &dst);
-	if (client_fd < 0)
+	client_fd = client_socket(family, t->sotype, NULL);
+	if (!ASSERT_OK_FD(client_fd, "client_socket"))
 		goto close_srv;
 
-	err = connect(client_fd, (void *)&dst, inetaddr_len(&dst));
+	err = make_sockaddr(family, t->connect_to.ip, t->connect_to.port, &dst, &len);
+	if (!ASSERT_OK(err, "make_sockaddr"))
+		goto close_all;
+	err = connect(client_fd, (void *)&dst, len);
 	if (t->sotype == SOCK_DGRAM) {
 		err = send_byte(client_fd);
 		if (err)
@@ -976,9 +917,11 @@ static void test_drop_on_lookup(struct test_sk_lookup *skel)
 
 static void drop_on_reuseport(const struct test *t)
 {
+	int family = is_ipv6(t->connect_to.ip) ? AF_INET6 : AF_INET;
 	struct sockaddr_storage dst = { 0 };
 	int client, server1, server2, err;
 	struct bpf_link *lookup_link;
+	socklen_t len;
 	ssize_t n;
 
 	lookup_link = attach_lookup_prog(t->lookup_prog);
@@ -1000,12 +943,14 @@ static void drop_on_reuseport(const struct test *t)
 	if (server2 < 0)
 		goto close_srv1;
 
-	client = make_socket(t->sotype, t->connect_to.ip,
-			     t->connect_to.port, &dst);
-	if (client < 0)
+	client = client_socket(family, t->sotype, NULL);
+	if (!ASSERT_OK_FD(client, "client_socket"))
 		goto close_srv2;
 
-	err = connect(client, (void *)&dst, inetaddr_len(&dst));
+	err = make_sockaddr(family, t->connect_to.ip, t->connect_to.port, &dst, &len);
+	if (!ASSERT_OK(err, "make_sockaddr"))
+		goto close_all;
+	err = connect(client, (void *)&dst, len);
 	if (t->sotype == SOCK_DGRAM) {
 		err = send_byte(client);
 		if (err)
@@ -1152,8 +1097,8 @@ static void run_sk_assign_connected(struct test_sk_lookup *skel,
 	if (server_fd < 0)
 		return;
 
-	connected_fd = make_client(sotype, EXT_IP4, EXT_PORT);
-	if (connected_fd < 0)
+	connected_fd = connect_to_addr_str(AF_INET, sotype, EXT_IP4, EXT_PORT, NULL);
+	if (!ASSERT_OK_FD(connected_fd, "connect_to_addr_str"))
 		goto out_close_server;
 
 	/* Put a connected socket in redirect map */
@@ -1166,8 +1111,8 @@ static void run_sk_assign_connected(struct test_sk_lookup *skel,
 		goto out_close_connected;
 
 	/* Try to redirect TCP SYN / UDP packet to a connected socket */
-	client_fd = make_client(sotype, EXT_IP4, EXT_PORT);
-	if (client_fd < 0)
+	client_fd = connect_to_addr_str(AF_INET, sotype, EXT_IP4, EXT_PORT, NULL);
+	if (!ASSERT_OK_FD(client_fd, "connect_to_addr_str"))
 		goto out_unlink_prog;
 	if (sotype == SOCK_DGRAM) {
 		send_byte(client_fd);
@@ -1219,6 +1164,7 @@ static void run_multi_prog_lookup(const struct test_multi_prog *t)
 	int map_fd, server_fd, client_fd;
 	struct bpf_link *link1, *link2;
 	int prog_idx, done, err;
+	socklen_t len;
 
 	map_fd = bpf_map__fd(t->run_map);
 
@@ -1248,11 +1194,14 @@ static void run_multi_prog_lookup(const struct test_multi_prog *t)
 	if (err)
 		goto out_close_server;
 
-	client_fd = make_socket(SOCK_STREAM, EXT_IP4, EXT_PORT, &dst);
-	if (client_fd < 0)
+	client_fd = client_socket(AF_INET, SOCK_STREAM, NULL);
+	if (!ASSERT_OK_FD(client_fd, "client_socket"))
 		goto out_close_server;
 
-	err = connect(client_fd, (void *)&dst, inetaddr_len(&dst));
+	err = make_sockaddr(AF_INET, EXT_IP4, EXT_PORT, &dst, &len);
+	if (!ASSERT_OK(err, "make_sockaddr"))
+		goto out_close_client;
+	err = connect(client_fd, (void *)&dst, len);
 	if (CHECK(err && !t->expect_errno, "connect",
 		  "unexpected error %d\n", errno))
 		goto out_close_client;
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_addr.c b/tools/testing/selftests/bpf/prog_tests/sock_addr.c
index b880c564a204..a6ee7f8d4f79 100644
--- a/tools/testing/selftests/bpf/prog_tests/sock_addr.c
+++ b/tools/testing/selftests/bpf/prog_tests/sock_addr.c
@@ -2642,6 +2642,7 @@ void test_sock_addr(void)
 			break;
 		default:
 			ASSERT_TRUE(false, "Unknown sock addr test type");
+			err = -EINVAL;
 			break;
 		}
 
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index da5a6fb03b69..4ee1148d22be 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -1836,6 +1836,7 @@ static void test_udp_unix_redir(struct test_sockmap_listen *skel, struct bpf_map
 				int family)
 {
 	const char *family_name, *map_name;
+	struct netns_obj *netns;
 	char s[MAX_TEST_NAME];
 
 	family_name = family_str(family);
@@ -1843,8 +1844,15 @@ static void test_udp_unix_redir(struct test_sockmap_listen *skel, struct bpf_map
 	snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__);
 	if (!test__start_subtest(s))
 		return;
+
+	netns = netns_new("sockmap_listen", true);
+	if (!ASSERT_OK_PTR(netns, "netns_new"))
+		return;
+
 	inet_unix_skb_redir_to_connected(skel, map, family);
 	unix_inet_skb_redir_to_connected(skel, map, family);
+
+	netns_free(netns);
 }
 
 static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index 59993fc9c0d7..21c5a37846ad 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -3,7 +3,10 @@
 #include <test_progs.h>
 #include <network_helpers.h>
 #include "tailcall_poke.skel.h"
-
+#include "tailcall_bpf2bpf_hierarchy2.skel.h"
+#include "tailcall_bpf2bpf_hierarchy3.skel.h"
+#include "tailcall_freplace.skel.h"
+#include "tc_bpf2bpf.skel.h"
 
 /* test_tailcall_1 checks basic functionality by patching multiple locations
  * in a single program for a single tail call slot with nop->jmp, jmp->nop
@@ -1187,6 +1190,372 @@ out:
 	tailcall_poke__destroy(call);
 }
 
+static void test_tailcall_hierarchy_count(const char *which, bool test_fentry,
+					  bool test_fexit,
+					  bool test_fentry_entry)
+{
+	int err, map_fd, prog_fd, main_data_fd, fentry_data_fd, fexit_data_fd, i, val;
+	struct bpf_object *obj = NULL, *fentry_obj = NULL, *fexit_obj = NULL;
+	struct bpf_link *fentry_link = NULL, *fexit_link = NULL;
+	struct bpf_program *prog, *fentry_prog;
+	struct bpf_map *prog_array, *data_map;
+	int fentry_prog_fd;
+	char buff[128] = {};
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = buff,
+		.data_size_in = sizeof(buff),
+		.repeat = 1,
+	);
+
+	err = bpf_prog_test_load(which, BPF_PROG_TYPE_SCHED_CLS, &obj,
+				 &prog_fd);
+	if (!ASSERT_OK(err, "load obj"))
+		return;
+
+	prog = bpf_object__find_program_by_name(obj, "entry");
+	if (!ASSERT_OK_PTR(prog, "find entry prog"))
+		goto out;
+
+	prog_fd = bpf_program__fd(prog);
+	if (!ASSERT_GE(prog_fd, 0, "prog_fd"))
+		goto out;
+
+	if (test_fentry_entry) {
+		fentry_obj = bpf_object__open_file("tailcall_bpf2bpf_hierarchy_fentry.bpf.o",
+						   NULL);
+		if (!ASSERT_OK_PTR(fentry_obj, "open fentry_obj file"))
+			goto out;
+
+		fentry_prog = bpf_object__find_program_by_name(fentry_obj,
+							       "fentry");
+		if (!ASSERT_OK_PTR(prog, "find fentry prog"))
+			goto out;
+
+		err = bpf_program__set_attach_target(fentry_prog, prog_fd,
+						     "entry");
+		if (!ASSERT_OK(err, "set_attach_target entry"))
+			goto out;
+
+		err = bpf_object__load(fentry_obj);
+		if (!ASSERT_OK(err, "load fentry_obj"))
+			goto out;
+
+		fentry_link = bpf_program__attach_trace(fentry_prog);
+		if (!ASSERT_OK_PTR(fentry_link, "attach_trace"))
+			goto out;
+
+		fentry_prog_fd = bpf_program__fd(fentry_prog);
+		if (!ASSERT_GE(fentry_prog_fd, 0, "fentry_prog_fd"))
+			goto out;
+
+		prog_array = bpf_object__find_map_by_name(fentry_obj, "jmp_table");
+		if (!ASSERT_OK_PTR(prog_array, "find jmp_table"))
+			goto out;
+
+		map_fd = bpf_map__fd(prog_array);
+		if (!ASSERT_GE(map_fd, 0, "map_fd"))
+			goto out;
+
+		i = 0;
+		err = bpf_map_update_elem(map_fd, &i, &fentry_prog_fd, BPF_ANY);
+		if (!ASSERT_OK(err, "update jmp_table"))
+			goto out;
+
+		data_map = bpf_object__find_map_by_name(fentry_obj, ".bss");
+		if (!ASSERT_FALSE(!data_map || !bpf_map__is_internal(data_map),
+				  "find data_map"))
+			goto out;
+
+	} else {
+		prog_array = bpf_object__find_map_by_name(obj, "jmp_table");
+		if (!ASSERT_OK_PTR(prog_array, "find jmp_table"))
+			goto out;
+
+		map_fd = bpf_map__fd(prog_array);
+		if (!ASSERT_GE(map_fd, 0, "map_fd"))
+			goto out;
+
+		i = 0;
+		err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+		if (!ASSERT_OK(err, "update jmp_table"))
+			goto out;
+
+		data_map = bpf_object__find_map_by_name(obj, ".bss");
+		if (!ASSERT_FALSE(!data_map || !bpf_map__is_internal(data_map),
+				  "find data_map"))
+			goto out;
+	}
+
+	if (test_fentry) {
+		fentry_obj = bpf_object__open_file("tailcall_bpf2bpf_fentry.bpf.o",
+						   NULL);
+		if (!ASSERT_OK_PTR(fentry_obj, "open fentry_obj file"))
+			goto out;
+
+		prog = bpf_object__find_program_by_name(fentry_obj, "fentry");
+		if (!ASSERT_OK_PTR(prog, "find fentry prog"))
+			goto out;
+
+		err = bpf_program__set_attach_target(prog, prog_fd,
+						     "subprog_tail");
+		if (!ASSERT_OK(err, "set_attach_target subprog_tail"))
+			goto out;
+
+		err = bpf_object__load(fentry_obj);
+		if (!ASSERT_OK(err, "load fentry_obj"))
+			goto out;
+
+		fentry_link = bpf_program__attach_trace(prog);
+		if (!ASSERT_OK_PTR(fentry_link, "attach_trace"))
+			goto out;
+	}
+
+	if (test_fexit) {
+		fexit_obj = bpf_object__open_file("tailcall_bpf2bpf_fexit.bpf.o",
+						  NULL);
+		if (!ASSERT_OK_PTR(fexit_obj, "open fexit_obj file"))
+			goto out;
+
+		prog = bpf_object__find_program_by_name(fexit_obj, "fexit");
+		if (!ASSERT_OK_PTR(prog, "find fexit prog"))
+			goto out;
+
+		err = bpf_program__set_attach_target(prog, prog_fd,
+						     "subprog_tail");
+		if (!ASSERT_OK(err, "set_attach_target subprog_tail"))
+			goto out;
+
+		err = bpf_object__load(fexit_obj);
+		if (!ASSERT_OK(err, "load fexit_obj"))
+			goto out;
+
+		fexit_link = bpf_program__attach_trace(prog);
+		if (!ASSERT_OK_PTR(fexit_link, "attach_trace"))
+			goto out;
+	}
+
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, 1, "tailcall retval");
+
+	main_data_fd = bpf_map__fd(data_map);
+	if (!ASSERT_GE(main_data_fd, 0, "main_data_fd"))
+		goto out;
+
+	i = 0;
+	err = bpf_map_lookup_elem(main_data_fd, &i, &val);
+	ASSERT_OK(err, "tailcall count");
+	ASSERT_EQ(val, 34, "tailcall count");
+
+	if (test_fentry) {
+		data_map = bpf_object__find_map_by_name(fentry_obj, ".bss");
+		if (!ASSERT_FALSE(!data_map || !bpf_map__is_internal(data_map),
+				  "find tailcall_bpf2bpf_fentry.bss map"))
+			goto out;
+
+		fentry_data_fd = bpf_map__fd(data_map);
+		if (!ASSERT_GE(fentry_data_fd, 0,
+				  "find tailcall_bpf2bpf_fentry.bss map fd"))
+			goto out;
+
+		i = 0;
+		err = bpf_map_lookup_elem(fentry_data_fd, &i, &val);
+		ASSERT_OK(err, "fentry count");
+		ASSERT_EQ(val, 68, "fentry count");
+	}
+
+	if (test_fexit) {
+		data_map = bpf_object__find_map_by_name(fexit_obj, ".bss");
+		if (!ASSERT_FALSE(!data_map || !bpf_map__is_internal(data_map),
+				  "find tailcall_bpf2bpf_fexit.bss map"))
+			goto out;
+
+		fexit_data_fd = bpf_map__fd(data_map);
+		if (!ASSERT_GE(fexit_data_fd, 0,
+				  "find tailcall_bpf2bpf_fexit.bss map fd"))
+			goto out;
+
+		i = 0;
+		err = bpf_map_lookup_elem(fexit_data_fd, &i, &val);
+		ASSERT_OK(err, "fexit count");
+		ASSERT_EQ(val, 68, "fexit count");
+	}
+
+	i = 0;
+	err = bpf_map_delete_elem(map_fd, &i);
+	if (!ASSERT_OK(err, "delete_elem from jmp_table"))
+		goto out;
+
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, 1, "tailcall retval");
+
+	i = 0;
+	err = bpf_map_lookup_elem(main_data_fd, &i, &val);
+	ASSERT_OK(err, "tailcall count");
+	ASSERT_EQ(val, 35, "tailcall count");
+
+	if (test_fentry) {
+		i = 0;
+		err = bpf_map_lookup_elem(fentry_data_fd, &i, &val);
+		ASSERT_OK(err, "fentry count");
+		ASSERT_EQ(val, 70, "fentry count");
+	}
+
+	if (test_fexit) {
+		i = 0;
+		err = bpf_map_lookup_elem(fexit_data_fd, &i, &val);
+		ASSERT_OK(err, "fexit count");
+		ASSERT_EQ(val, 70, "fexit count");
+	}
+
+out:
+	bpf_link__destroy(fentry_link);
+	bpf_link__destroy(fexit_link);
+	bpf_object__close(fentry_obj);
+	bpf_object__close(fexit_obj);
+	bpf_object__close(obj);
+}
+
+/* test_tailcall_bpf2bpf_hierarchy_1 checks that the count value of the tail
+ * call limit enforcement matches with expectations when tailcalls are preceded
+ * with two bpf2bpf calls.
+ *
+ *         subprog --tailcall-> entry
+ * entry <
+ *         subprog --tailcall-> entry
+ */
+static void test_tailcall_bpf2bpf_hierarchy_1(void)
+{
+	test_tailcall_hierarchy_count("tailcall_bpf2bpf_hierarchy1.bpf.o",
+				      false, false, false);
+}
+
+/* test_tailcall_bpf2bpf_hierarchy_fentry checks that the count value of the
+ * tail call limit enforcement matches with expectations when tailcalls are
+ * preceded with two bpf2bpf calls, and the two subprogs are traced by fentry.
+ */
+static void test_tailcall_bpf2bpf_hierarchy_fentry(void)
+{
+	test_tailcall_hierarchy_count("tailcall_bpf2bpf_hierarchy1.bpf.o",
+				      true, false, false);
+}
+
+/* test_tailcall_bpf2bpf_hierarchy_fexit checks that the count value of the tail
+ * call limit enforcement matches with expectations when tailcalls are preceded
+ * with two bpf2bpf calls, and the two subprogs are traced by fexit.
+ */
+static void test_tailcall_bpf2bpf_hierarchy_fexit(void)
+{
+	test_tailcall_hierarchy_count("tailcall_bpf2bpf_hierarchy1.bpf.o",
+				      false, true, false);
+}
+
+/* test_tailcall_bpf2bpf_hierarchy_fentry_fexit checks that the count value of
+ * the tail call limit enforcement matches with expectations when tailcalls are
+ * preceded with two bpf2bpf calls, and the two subprogs are traced by both
+ * fentry and fexit.
+ */
+static void test_tailcall_bpf2bpf_hierarchy_fentry_fexit(void)
+{
+	test_tailcall_hierarchy_count("tailcall_bpf2bpf_hierarchy1.bpf.o",
+				      true, true, false);
+}
+
+/* test_tailcall_bpf2bpf_hierarchy_fentry_entry checks that the count value of
+ * the tail call limit enforcement matches with expectations when tailcalls are
+ * preceded with two bpf2bpf calls in fentry.
+ */
+static void test_tailcall_bpf2bpf_hierarchy_fentry_entry(void)
+{
+	test_tailcall_hierarchy_count("tc_dummy.bpf.o", false, false, true);
+}
+
+/* test_tailcall_bpf2bpf_hierarchy_2 checks that the count value of the tail
+ * call limit enforcement matches with expectations:
+ *
+ *         subprog_tail0 --tailcall-> classifier_0 -> subprog_tail0
+ * entry <
+ *         subprog_tail1 --tailcall-> classifier_1 -> subprog_tail1
+ */
+static void test_tailcall_bpf2bpf_hierarchy_2(void)
+{
+	RUN_TESTS(tailcall_bpf2bpf_hierarchy2);
+}
+
+/* test_tailcall_bpf2bpf_hierarchy_3 checks that the count value of the tail
+ * call limit enforcement matches with expectations:
+ *
+ *                                   subprog with jmp_table0 to classifier_0
+ * entry --tailcall-> classifier_0 <
+ *                                   subprog with jmp_table1 to classifier_0
+ */
+static void test_tailcall_bpf2bpf_hierarchy_3(void)
+{
+	RUN_TESTS(tailcall_bpf2bpf_hierarchy3);
+}
+
+/* test_tailcall_freplace checks that the attached freplace prog is OK to
+ * update the prog_array map.
+ */
+static void test_tailcall_freplace(void)
+{
+	struct tailcall_freplace *freplace_skel = NULL;
+	struct bpf_link *freplace_link = NULL;
+	struct bpf_program *freplace_prog;
+	struct tc_bpf2bpf *tc_skel = NULL;
+	int prog_fd, map_fd;
+	char buff[128] = {};
+	int err, key;
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .data_in = buff,
+		    .data_size_in = sizeof(buff),
+		    .repeat = 1,
+	);
+
+	freplace_skel = tailcall_freplace__open();
+	if (!ASSERT_OK_PTR(freplace_skel, "tailcall_freplace__open"))
+		return;
+
+	tc_skel = tc_bpf2bpf__open_and_load();
+	if (!ASSERT_OK_PTR(tc_skel, "tc_bpf2bpf__open_and_load"))
+		goto out;
+
+	prog_fd = bpf_program__fd(tc_skel->progs.entry_tc);
+	freplace_prog = freplace_skel->progs.entry_freplace;
+	err = bpf_program__set_attach_target(freplace_prog, prog_fd, "subprog");
+	if (!ASSERT_OK(err, "set_attach_target"))
+		goto out;
+
+	err = tailcall_freplace__load(freplace_skel);
+	if (!ASSERT_OK(err, "tailcall_freplace__load"))
+		goto out;
+
+	freplace_link = bpf_program__attach_freplace(freplace_prog, prog_fd,
+						     "subprog");
+	if (!ASSERT_OK_PTR(freplace_link, "attach_freplace"))
+		goto out;
+
+	map_fd = bpf_map__fd(freplace_skel->maps.jmp_table);
+	prog_fd = bpf_program__fd(freplace_prog);
+	key = 0;
+	err = bpf_map_update_elem(map_fd, &key, &prog_fd, BPF_ANY);
+	if (!ASSERT_OK(err, "update jmp_table"))
+		goto out;
+
+	prog_fd = bpf_program__fd(tc_skel->progs.entry_tc);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(topts.retval, 34, "test_run retval");
+
+out:
+	bpf_link__destroy(freplace_link);
+	tc_bpf2bpf__destroy(tc_skel);
+	tailcall_freplace__destroy(freplace_skel);
+}
+
 void test_tailcalls(void)
 {
 	if (test__start_subtest("tailcall_1"))
@@ -1223,4 +1592,18 @@ void test_tailcalls(void)
 		test_tailcall_bpf2bpf_fentry_entry();
 	if (test__start_subtest("tailcall_poke"))
 		test_tailcall_poke();
+	if (test__start_subtest("tailcall_bpf2bpf_hierarchy_1"))
+		test_tailcall_bpf2bpf_hierarchy_1();
+	if (test__start_subtest("tailcall_bpf2bpf_hierarchy_fentry"))
+		test_tailcall_bpf2bpf_hierarchy_fentry();
+	if (test__start_subtest("tailcall_bpf2bpf_hierarchy_fexit"))
+		test_tailcall_bpf2bpf_hierarchy_fexit();
+	if (test__start_subtest("tailcall_bpf2bpf_hierarchy_fentry_fexit"))
+		test_tailcall_bpf2bpf_hierarchy_fentry_fexit();
+	if (test__start_subtest("tailcall_bpf2bpf_hierarchy_fentry_entry"))
+		test_tailcall_bpf2bpf_hierarchy_fentry_entry();
+	test_tailcall_bpf2bpf_hierarchy_2();
+	test_tailcall_bpf2bpf_hierarchy_3();
+	if (test__start_subtest("tailcall_freplace"))
+		test_tailcall_freplace();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
index 196abf223465..f77f604389aa 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_opts.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
@@ -2384,7 +2384,7 @@ static int generate_dummy_prog(void)
 		BPF_MOV64_IMM(BPF_REG_0, 0),
 		BPF_EXIT_INSN(),
 	};
-	const size_t prog_insn_cnt = sizeof(prog_insns) / sizeof(struct bpf_insn);
+	const size_t prog_insn_cnt = ARRAY_SIZE(prog_insns);
 	LIBBPF_OPTS(bpf_prog_load_opts, opts);
 	const size_t log_buf_sz = 256;
 	char log_buf[log_buf_sz];
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
index 327d51f59142..c85798966aec 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
@@ -68,6 +68,7 @@
 		__FILE__, __LINE__, strerror(errno), ##__VA_ARGS__)
 
 static const char * const namespaces[] = {NS_SRC, NS_FWD, NS_DST, NULL};
+static struct netns_obj *netns_objs[3];
 
 static int write_file(const char *path, const char *newval)
 {
@@ -87,27 +88,41 @@ static int write_file(const char *path, const char *newval)
 
 static int netns_setup_namespaces(const char *verb)
 {
+	struct netns_obj **ns_obj = netns_objs;
 	const char * const *ns = namespaces;
-	char cmd[128];
 
 	while (*ns) {
-		snprintf(cmd, sizeof(cmd), "ip netns %s %s", verb, *ns);
-		if (!ASSERT_OK(system(cmd), cmd))
-			return -1;
+		if (strcmp(verb, "add") == 0) {
+			*ns_obj = netns_new(*ns, false);
+			if (!ASSERT_OK_PTR(*ns_obj, "netns_new"))
+				return -1;
+		} else {
+			if (!ASSERT_OK_PTR(*ns_obj, "netns_obj is NULL"))
+				return -1;
+			netns_free(*ns_obj);
+			*ns_obj = NULL;
+		}
 		ns++;
+		ns_obj++;
 	}
 	return 0;
 }
 
 static void netns_setup_namespaces_nofail(const char *verb)
 {
+	struct netns_obj **ns_obj = netns_objs;
 	const char * const *ns = namespaces;
-	char cmd[128];
 
 	while (*ns) {
-		snprintf(cmd, sizeof(cmd), "ip netns %s %s > /dev/null 2>&1", verb, *ns);
-		system(cmd);
+		if (strcmp(verb, "add") == 0) {
+			*ns_obj = netns_new(*ns, false);
+		} else {
+			if (*ns_obj)
+				netns_free(*ns_obj);
+			*ns_obj = NULL;
+		}
 		ns++;
+		ns_obj++;
 	}
 }
 
@@ -471,7 +486,7 @@ static int set_forwarding(bool enable)
 
 static int __rcv_tstamp(int fd, const char *expected, size_t s, __u64 *tstamp)
 {
-	struct __kernel_timespec pkt_ts = {};
+	struct timespec pkt_ts = {};
 	char ctl[CMSG_SPACE(sizeof(pkt_ts))];
 	struct timespec now_ts;
 	struct msghdr msg = {};
@@ -495,7 +510,7 @@ static int __rcv_tstamp(int fd, const char *expected, size_t s, __u64 *tstamp)
 
 	cmsg = CMSG_FIRSTHDR(&msg);
 	if (cmsg && cmsg->cmsg_level == SOL_SOCKET &&
-	    cmsg->cmsg_type == SO_TIMESTAMPNS_NEW)
+	    cmsg->cmsg_type == SO_TIMESTAMPNS)
 		memcpy(&pkt_ts, CMSG_DATA(cmsg), sizeof(pkt_ts));
 
 	pkt_ns = pkt_ts.tv_sec * NSEC_PER_SEC + pkt_ts.tv_nsec;
@@ -537,9 +552,9 @@ static int wait_netstamp_needed_key(void)
 	if (!ASSERT_GE(srv_fd, 0, "start_server"))
 		goto done;
 
-	err = setsockopt(srv_fd, SOL_SOCKET, SO_TIMESTAMPNS_NEW,
+	err = setsockopt(srv_fd, SOL_SOCKET, SO_TIMESTAMPNS,
 			 &opt, sizeof(opt));
-	if (!ASSERT_OK(err, "setsockopt(SO_TIMESTAMPNS_NEW)"))
+	if (!ASSERT_OK(err, "setsockopt(SO_TIMESTAMPNS)"))
 		goto done;
 
 	cli_fd = connect_to_fd(srv_fd, TIMEOUT_MILLIS);
@@ -621,9 +636,9 @@ static void test_inet_dtime(int family, int type, const char *addr, __u16 port)
 		return;
 
 	/* Ensure the kernel puts the (rcv) timestamp for all skb */
-	err = setsockopt(listen_fd, SOL_SOCKET, SO_TIMESTAMPNS_NEW,
+	err = setsockopt(listen_fd, SOL_SOCKET, SO_TIMESTAMPNS,
 			 &opt, sizeof(opt));
-	if (!ASSERT_OK(err, "setsockopt(SO_TIMESTAMPNS_NEW)"))
+	if (!ASSERT_OK(err, "setsockopt(SO_TIMESTAMPNS)"))
 		goto done;
 
 	if (type == SOCK_STREAM) {
@@ -857,7 +872,7 @@ static void test_tcp_dtime(struct test_tc_dtime *skel, int family, bool bpf_fwd)
 	test_inet_dtime(family, SOCK_STREAM, addr, 50000 + t);
 
 	/* fwdns_prio100 prog does not read delivery_time_type, so
-	 * kernel puts the (rcv) timetamp in __sk_buff->tstamp
+	 * kernel puts the (rcv) timestamp in __sk_buff->tstamp
 	 */
 	ASSERT_EQ(dtimes[INGRESS_FWDNS_P100], 0,
 		  dtime_cnt_str(t, INGRESS_FWDNS_P100));
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
index f2b99d95d916..c38784c1c066 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
 #include <test_progs.h>
 #include "cgroup_helpers.h"
 #include "network_helpers.h"
diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c
index 2900c5e9a016..1750c29b94f8 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c
@@ -38,11 +38,7 @@ void test_bpf_syscall_macro(void)
 	/* check whether args of syscall are copied correctly */
 	prctl(exp_arg1, exp_arg2, exp_arg3, exp_arg4, exp_arg5);
 
-#if defined(__aarch64__) || defined(__s390__)
-	ASSERT_NEQ(skel->bss->arg1, exp_arg1, "syscall_arg1");
-#else
 	ASSERT_EQ(skel->bss->arg1, exp_arg1, "syscall_arg1");
-#endif
 	ASSERT_EQ(skel->bss->arg2, exp_arg2, "syscall_arg2");
 	ASSERT_EQ(skel->bss->arg3, exp_arg3, "syscall_arg3");
 	/* it cannot copy arg4 when uses PT_REGS_PARM4 on x86_64 */
diff --git a/tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c b/tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c
index a0054019e677..9c0200c132d9 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c
@@ -51,7 +51,7 @@ static int run_set_secureexec(int map_fd, int secureexec)
 			exit(ret);
 
 		/* If the binary is executed with securexec=1, the dynamic
-		 * loader ingores and unsets certain variables like LD_PRELOAD,
+		 * loader ignores and unsets certain variables like LD_PRELOAD,
 		 * TMPDIR etc. TMPDIR is used here to simplify the example, as
 		 * LD_PRELOAD requires a real .so file.
 		 *
diff --git a/tools/testing/selftests/bpf/prog_tests/test_lsm.c b/tools/testing/selftests/bpf/prog_tests/test_lsm.c
index 16175d579bc7..2a27f3714f5c 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_lsm.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_lsm.c
@@ -12,6 +12,7 @@
 #include <stdlib.h>
 
 #include "lsm.skel.h"
+#include "lsm_tailcall.skel.h"
 
 char *CMD_ARGS[] = {"true", NULL};
 
@@ -95,7 +96,7 @@ static int test_lsm(struct lsm *skel)
 	return 0;
 }
 
-void test_test_lsm(void)
+static void test_lsm_basic(void)
 {
 	struct lsm *skel = NULL;
 	int err;
@@ -114,3 +115,46 @@ void test_test_lsm(void)
 close_prog:
 	lsm__destroy(skel);
 }
+
+static void test_lsm_tailcall(void)
+{
+	struct lsm_tailcall *skel = NULL;
+	int map_fd, prog_fd;
+	int err, key;
+
+	skel = lsm_tailcall__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "lsm_tailcall__skel_load"))
+		goto close_prog;
+
+	map_fd = bpf_map__fd(skel->maps.jmp_table);
+	if (CHECK_FAIL(map_fd < 0))
+		goto close_prog;
+
+	prog_fd = bpf_program__fd(skel->progs.lsm_file_permission_prog);
+	if (CHECK_FAIL(prog_fd < 0))
+		goto close_prog;
+
+	key = 0;
+	err = bpf_map_update_elem(map_fd, &key, &prog_fd, BPF_ANY);
+	if (CHECK_FAIL(!err))
+		goto close_prog;
+
+	prog_fd = bpf_program__fd(skel->progs.lsm_file_alloc_security_prog);
+	if (CHECK_FAIL(prog_fd < 0))
+		goto close_prog;
+
+	err = bpf_map_update_elem(map_fd, &key, &prog_fd, BPF_ANY);
+	if (CHECK_FAIL(err))
+		goto close_prog;
+
+close_prog:
+	lsm_tailcall__destroy(skel);
+}
+
+void test_test_lsm(void)
+{
+	if (test__start_subtest("lsm_basic"))
+		test_lsm_basic();
+	if (test__start_subtest("lsm_tailcall"))
+		test_lsm_tailcall();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_mmap_inner_array.c b/tools/testing/selftests/bpf/prog_tests/test_mmap_inner_array.c
new file mode 100644
index 000000000000..ce745776ed18
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_mmap_inner_array.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <sys/mman.h>
+#include "mmap_inner_array.skel.h"
+
+void test_mmap_inner_array(void)
+{
+	const long page_size = sysconf(_SC_PAGE_SIZE);
+	struct mmap_inner_array *skel;
+	int inner_array_fd, err;
+	void *tmp;
+	__u64 *val;
+
+	skel = mmap_inner_array__open_and_load();
+
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	inner_array_fd = bpf_map__fd(skel->maps.inner_array);
+	tmp = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, inner_array_fd, 0);
+	if (!ASSERT_OK_PTR(tmp, "inner array mmap"))
+		goto out;
+	val = (void *)tmp;
+
+	err = mmap_inner_array__attach(skel);
+	if (!ASSERT_OK(err, "attach"))
+		goto out_unmap;
+
+	skel->bss->pid = getpid();
+	usleep(1);
+
+	/* pid is set, pid_match == true and outer_map_match == false */
+	ASSERT_TRUE(skel->bss->pid_match, "pid match 1");
+	ASSERT_FALSE(skel->bss->outer_map_match, "outer map match 1");
+	ASSERT_FALSE(skel->bss->done, "done 1");
+	ASSERT_EQ(*val, 0, "value match 1");
+
+	err = bpf_map__update_elem(skel->maps.outer_map,
+				   &skel->bss->pid, sizeof(skel->bss->pid),
+				   &inner_array_fd, sizeof(inner_array_fd),
+				   BPF_ANY);
+	if (!ASSERT_OK(err, "update elem"))
+		goto out_unmap;
+	usleep(1);
+
+	/* outer map key is set, outer_map_match == true */
+	ASSERT_TRUE(skel->bss->pid_match, "pid match 2");
+	ASSERT_TRUE(skel->bss->outer_map_match, "outer map match 2");
+	ASSERT_TRUE(skel->bss->done, "done 2");
+	ASSERT_EQ(*val, skel->data->match_value, "value match 2");
+
+out_unmap:
+	munmap(tmp, page_size);
+out:
+	mmap_inner_array__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_strncmp.c b/tools/testing/selftests/bpf/prog_tests/test_strncmp.c
index 7ddd6615b7e7..baceb0de9d49 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_strncmp.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_strncmp.c
@@ -72,7 +72,7 @@ static void test_strncmp_ret(void)
 	got = trigger_strncmp(skel);
 	ASSERT_EQ(got, 0, "strncmp: same str");
 
-	/* Not-null-termainted string  */
+	/* Not-null-terminated string  */
 	memcpy(skel->bss->str, skel->rodata->target, sizeof(skel->bss->str));
 	skel->bss->str[sizeof(skel->bss->str) - 1] = 'A';
 	got = trigger_strncmp(skel);
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
index bbcf12696a6b..75a0dea511b3 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c
@@ -9,6 +9,7 @@
 #include "struct_ops_nulled_out_cb.skel.h"
 #include "struct_ops_forgotten_cb.skel.h"
 #include "struct_ops_detach.skel.h"
+#include "unsupported_ops.skel.h"
 
 static void check_map_info(struct bpf_map_info *info)
 {
@@ -311,5 +312,6 @@ void serial_test_struct_ops_module(void)
 		test_struct_ops_forgotten_cb();
 	if (test__start_subtest("test_detach_link"))
 		test_detach_link();
+	RUN_TESTS(unsupported_ops);
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/test_xdp_veth.c b/tools/testing/selftests/bpf/prog_tests/test_xdp_veth.c
new file mode 100644
index 000000000000..8d75424fe6bc
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_xdp_veth.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Create 3 namespaces with 3 veth peers, and forward packets in-between using
+ * native XDP
+ *
+ *                      XDP_TX
+ * NS1(veth11)        NS2(veth22)        NS3(veth33)
+ *      |                  |                  |
+ *      |                  |                  |
+ *   (veth1,            (veth2,            (veth3,
+ *   id:111)            id:122)            id:133)
+ *     ^ |                ^ |                ^ |
+ *     | |  XDP_REDIRECT  | |  XDP_REDIRECT  | |
+ *     | ------------------ ------------------ |
+ *     -----------------------------------------
+ *                    XDP_REDIRECT
+ */
+
+#define _GNU_SOURCE
+#include <net/if.h>
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "xdp_dummy.skel.h"
+#include "xdp_redirect_map.skel.h"
+#include "xdp_tx.skel.h"
+
+#define VETH_PAIRS_COUNT	3
+#define NS_SUFFIX_LEN		6
+#define VETH_NAME_MAX_LEN	16
+#define IP_SRC				"10.1.1.11"
+#define IP_DST				"10.1.1.33"
+#define IP_CMD_MAX_LEN		128
+
+struct skeletons {
+	struct xdp_dummy *xdp_dummy;
+	struct xdp_tx *xdp_tx;
+	struct xdp_redirect_map *xdp_redirect_maps;
+};
+
+struct veth_configuration {
+	char local_veth[VETH_NAME_MAX_LEN]; /* Interface in main namespace */
+	char remote_veth[VETH_NAME_MAX_LEN]; /* Peer interface in dedicated namespace*/
+	const char *namespace; /* Namespace for the remote veth */
+	char next_veth[VETH_NAME_MAX_LEN]; /* Local interface to redirect traffic to */
+	char *remote_addr; /* IP address of the remote veth */
+};
+
+static struct veth_configuration config[VETH_PAIRS_COUNT] = {
+	{
+		.local_veth = "veth1",
+		.remote_veth = "veth11",
+		.next_veth = "veth2",
+		.remote_addr = IP_SRC,
+		.namespace = "ns-veth11"
+	},
+	{
+		.local_veth = "veth2",
+		.remote_veth = "veth22",
+		.next_veth = "veth3",
+		.remote_addr = NULL,
+		.namespace = "ns-veth22"
+	},
+	{
+		.local_veth = "veth3",
+		.remote_veth = "veth33",
+		.next_veth = "veth1",
+		.remote_addr = IP_DST,
+		.namespace = "ns-veth33"
+	}
+};
+
+static int attach_programs_to_veth_pair(struct skeletons *skeletons, int index)
+{
+	struct bpf_program *local_prog, *remote_prog;
+	struct bpf_link **local_link, **remote_link;
+	struct nstoken *nstoken;
+	struct bpf_link *link;
+	int interface;
+
+	switch (index) {
+	case 0:
+		local_prog = skeletons->xdp_redirect_maps->progs.xdp_redirect_map_0;
+		local_link = &skeletons->xdp_redirect_maps->links.xdp_redirect_map_0;
+		remote_prog = skeletons->xdp_dummy->progs.xdp_dummy_prog;
+		remote_link = &skeletons->xdp_dummy->links.xdp_dummy_prog;
+		break;
+	case 1:
+		local_prog = skeletons->xdp_redirect_maps->progs.xdp_redirect_map_1;
+		local_link = &skeletons->xdp_redirect_maps->links.xdp_redirect_map_1;
+		remote_prog = skeletons->xdp_tx->progs.xdp_tx;
+		remote_link = &skeletons->xdp_tx->links.xdp_tx;
+		break;
+	case 2:
+		local_prog = skeletons->xdp_redirect_maps->progs.xdp_redirect_map_2;
+		local_link = &skeletons->xdp_redirect_maps->links.xdp_redirect_map_2;
+		remote_prog = skeletons->xdp_dummy->progs.xdp_dummy_prog;
+		remote_link = &skeletons->xdp_dummy->links.xdp_dummy_prog;
+		break;
+	}
+	interface = if_nametoindex(config[index].local_veth);
+	if (!ASSERT_NEQ(interface, 0, "non zero interface index"))
+		return -1;
+	link = bpf_program__attach_xdp(local_prog, interface);
+	if (!ASSERT_OK_PTR(link, "attach xdp program to local veth"))
+		return -1;
+	*local_link = link;
+	nstoken = open_netns(config[index].namespace);
+	if (!ASSERT_OK_PTR(nstoken, "switch to remote veth namespace"))
+		return -1;
+	interface = if_nametoindex(config[index].remote_veth);
+	if (!ASSERT_NEQ(interface, 0, "non zero interface index")) {
+		close_netns(nstoken);
+		return -1;
+	}
+	link = bpf_program__attach_xdp(remote_prog, interface);
+	*remote_link = link;
+	close_netns(nstoken);
+	if (!ASSERT_OK_PTR(link, "attach xdp program to remote veth"))
+		return -1;
+
+	return 0;
+}
+
+static int configure_network(struct skeletons *skeletons)
+{
+	int interface_id;
+	int map_fd;
+	int err;
+	int i = 0;
+
+	/* First create and configure all interfaces */
+	for (i = 0; i < VETH_PAIRS_COUNT; i++) {
+		SYS(fail, "ip netns add %s", config[i].namespace);
+		SYS(fail, "ip link add %s type veth peer name %s netns %s",
+		    config[i].local_veth, config[i].remote_veth, config[i].namespace);
+		SYS(fail, "ip link set dev %s up", config[i].local_veth);
+		if (config[i].remote_addr)
+			SYS(fail, "ip -n %s addr add %s/24 dev %s",	config[i].namespace,
+			    config[i].remote_addr, config[i].remote_veth);
+		SYS(fail, "ip -n %s link set dev %s up", config[i].namespace,
+		    config[i].remote_veth);
+	}
+
+	/* Then configure the redirect map and attach programs to interfaces */
+	map_fd = bpf_map__fd(skeletons->xdp_redirect_maps->maps.tx_port);
+	if (!ASSERT_GE(map_fd, 0, "open redirect map"))
+		goto fail;
+	for (i = 0; i < VETH_PAIRS_COUNT; i++) {
+		interface_id = if_nametoindex(config[i].next_veth);
+		if (!ASSERT_NEQ(interface_id, 0, "non zero interface index"))
+			goto fail;
+		err = bpf_map_update_elem(map_fd, &i, &interface_id, BPF_ANY);
+		if (!ASSERT_OK(err, "configure interface redirection through map"))
+			goto fail;
+		if (attach_programs_to_veth_pair(skeletons, i))
+			goto fail;
+	}
+
+	return 0;
+
+fail:
+	return -1;
+}
+
+static void cleanup_network(void)
+{
+	int i;
+
+	/* Deleting namespaces is enough to automatically remove veth pairs as well
+	 */
+	for (i = 0; i < VETH_PAIRS_COUNT; i++)
+		SYS_NOFAIL("ip netns del %s", config[i].namespace);
+}
+
+static int check_ping(struct skeletons *skeletons)
+{
+	/* Test: if all interfaces are properly configured, we must be able to ping
+	 * veth33 from veth11
+	 */
+	return SYS_NOFAIL("ip netns exec %s ping -c 1 -W 1 %s > /dev/null",
+					  config[0].namespace, IP_DST);
+}
+
+void test_xdp_veth_redirect(void)
+{
+	struct skeletons skeletons = {};
+
+	skeletons.xdp_dummy = xdp_dummy__open_and_load();
+	if (!ASSERT_OK_PTR(skeletons.xdp_dummy, "xdp_dummy__open_and_load"))
+		return;
+
+	skeletons.xdp_tx = xdp_tx__open_and_load();
+	if (!ASSERT_OK_PTR(skeletons.xdp_tx, "xdp_tx__open_and_load"))
+		goto destroy_xdp_dummy;
+
+	skeletons.xdp_redirect_maps = xdp_redirect_map__open_and_load();
+	if (!ASSERT_OK_PTR(skeletons.xdp_redirect_maps, "xdp_redirect_map__open_and_load"))
+		goto destroy_xdp_tx;
+
+	if (configure_network(&skeletons))
+		goto destroy_xdp_redirect_map;
+
+	ASSERT_OK(check_ping(&skeletons), "ping");
+
+destroy_xdp_redirect_map:
+	xdp_redirect_map__destroy(skeletons.xdp_redirect_maps);
+destroy_xdp_tx:
+	xdp_tx__destroy(skeletons.xdp_tx);
+destroy_xdp_dummy:
+	xdp_dummy__destroy(skeletons.xdp_dummy);
+
+	cleanup_network();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/token.c b/tools/testing/selftests/bpf/prog_tests/token.c
index fc4a175d8d76..fe86e4fdb89c 100644
--- a/tools/testing/selftests/bpf/prog_tests/token.c
+++ b/tools/testing/selftests/bpf/prog_tests/token.c
@@ -867,7 +867,7 @@ static int userns_obj_priv_implicit_token(int mnt_fd, struct token_lsm *lsm_skel
 	}
 	unsetenv(TOKEN_ENVVAR);
 
-	/* now the same struct_ops skeleton should succeed thanks to libppf
+	/* now the same struct_ops skeleton should succeed thanks to libbpf
 	 * creating BPF token from /sys/fs/bpf mount point
 	 */
 	skel = dummy_st_ops_success__open_and_load();
@@ -929,7 +929,7 @@ static int userns_obj_priv_implicit_token_envvar(int mnt_fd, struct token_lsm *l
 	if (!ASSERT_OK(err, "setenv_token_path"))
 		goto err_out;
 
-	/* now the same struct_ops skeleton should succeed thanks to libppf
+	/* now the same struct_ops skeleton should succeed thanks to libbpf
 	 * creating BPF token from custom mount point
 	 */
 	skel = dummy_st_ops_success__open_and_load();
diff --git a/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c b/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c
index 0adf8d9475cb..472f4f9fa95f 100644
--- a/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c
+++ b/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c
@@ -7,6 +7,7 @@
 #include "test_unpriv_bpf_disabled.skel.h"
 
 #include "cap_helpers.h"
+#include "bpf_util.h"
 
 /* Using CAP_LAST_CAP is risky here, since it can get pulled in from
  * an old /usr/include/linux/capability.h and be < CAP_BPF; as a result
@@ -146,7 +147,7 @@ static void test_unpriv_bpf_disabled_negative(struct test_unpriv_bpf_disabled *s
 		BPF_MOV64_IMM(BPF_REG_0, 0),
 		BPF_EXIT_INSN(),
 	};
-	const size_t prog_insn_cnt = sizeof(prog_insns) / sizeof(struct bpf_insn);
+	const size_t prog_insn_cnt = ARRAY_SIZE(prog_insns);
 	LIBBPF_OPTS(bpf_prog_load_opts, load_opts);
 	struct bpf_map_info map_info = {};
 	__u32 map_info_len = sizeof(map_info);
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
index bf6ca8e3eb13..844f6fc8487b 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -6,6 +6,8 @@
 #include "uprobe_multi.skel.h"
 #include "uprobe_multi_bench.skel.h"
 #include "uprobe_multi_usdt.skel.h"
+#include "uprobe_multi_consumers.skel.h"
+#include "uprobe_multi_pid_filter.skel.h"
 #include "bpf/libbpf_internal.h"
 #include "testing_helpers.h"
 #include "../sdt.h"
@@ -38,6 +40,7 @@ struct child {
 	int pid;
 	int tid;
 	pthread_t thread;
+	char stack[65536];
 };
 
 static void release_child(struct child *child)
@@ -67,41 +70,54 @@ static void kick_child(struct child *child)
 	fflush(NULL);
 }
 
-static struct child *spawn_child(void)
+static int child_func(void *arg)
 {
-	static struct child child;
-	int err;
-	int c;
-
-	/* pipe to notify child to execute the trigger functions */
-	if (pipe(child.go))
-		return NULL;
+	struct child *child = arg;
+	int err, c;
 
-	child.pid = child.tid = fork();
-	if (child.pid < 0) {
-		release_child(&child);
-		errno = EINVAL;
-		return NULL;
-	}
+	close(child->go[1]);
 
-	/* child */
-	if (child.pid == 0) {
-		close(child.go[1]);
+	/* wait for parent's kick */
+	err = read(child->go[0], &c, 1);
+	if (err != 1)
+		exit(err);
 
-		/* wait for parent's kick */
-		err = read(child.go[0], &c, 1);
-		if (err != 1)
-			exit(err);
+	uprobe_multi_func_1();
+	uprobe_multi_func_2();
+	uprobe_multi_func_3();
+	usdt_trigger();
 
-		uprobe_multi_func_1();
-		uprobe_multi_func_2();
-		uprobe_multi_func_3();
-		usdt_trigger();
+	exit(errno);
+}
 
-		exit(errno);
+static int spawn_child_flag(struct child *child, bool clone_vm)
+{
+	/* pipe to notify child to execute the trigger functions */
+	if (pipe(child->go))
+		return -1;
+
+	if (clone_vm) {
+		child->pid = child->tid = clone(child_func, child->stack + sizeof(child->stack)/2,
+						CLONE_VM|SIGCHLD, child);
+	} else {
+		child->pid = child->tid = fork();
+	}
+	if (child->pid < 0) {
+		release_child(child);
+		errno = EINVAL;
+		return -1;
 	}
 
-	return &child;
+	/* fork-ed child */
+	if (!clone_vm && child->pid == 0)
+		child_func(child);
+
+	return 0;
+}
+
+static int spawn_child(struct child *child)
+{
+	return spawn_child_flag(child, false);
 }
 
 static void *child_thread(void *ctx)
@@ -130,39 +146,38 @@ static void *child_thread(void *ctx)
 	pthread_exit(&err);
 }
 
-static struct child *spawn_thread(void)
+static int spawn_thread(struct child *child)
 {
-	static struct child child;
 	int c, err;
 
 	/* pipe to notify child to execute the trigger functions */
-	if (pipe(child.go))
-		return NULL;
+	if (pipe(child->go))
+		return -1;
 	/* pipe to notify parent that child thread is ready */
-	if (pipe(child.c2p)) {
-		close(child.go[0]);
-		close(child.go[1]);
-		return NULL;
+	if (pipe(child->c2p)) {
+		close(child->go[0]);
+		close(child->go[1]);
+		return -1;
 	}
 
-	child.pid = getpid();
+	child->pid = getpid();
 
-	err = pthread_create(&child.thread, NULL, child_thread, &child);
+	err = pthread_create(&child->thread, NULL, child_thread, child);
 	if (err) {
 		err = -errno;
-		close(child.go[0]);
-		close(child.go[1]);
-		close(child.c2p[0]);
-		close(child.c2p[1]);
+		close(child->go[0]);
+		close(child->go[1]);
+		close(child->c2p[0]);
+		close(child->c2p[1]);
 		errno = -err;
-		return NULL;
+		return -1;
 	}
 
-	err = read(child.c2p[0], &c, 1);
+	err = read(child->c2p[0], &c, 1);
 	if (!ASSERT_EQ(err, 1, "child_thread_ready"))
-		return NULL;
+		return -1;
 
-	return &child;
+	return 0;
 }
 
 static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child)
@@ -198,7 +213,7 @@ static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child
 
 	/*
 	 * There are 2 entry and 2 exit probe called for each uprobe_multi_func_[123]
-	 * function and each slepable probe (6) increments uprobe_multi_sleep_result.
+	 * function and each sleepable probe (6) increments uprobe_multi_sleep_result.
 	 */
 	ASSERT_EQ(skel->bss->uprobe_multi_func_1_result, 2, "uprobe_multi_func_1_result");
 	ASSERT_EQ(skel->bss->uprobe_multi_func_2_result, 2, "uprobe_multi_func_2_result");
@@ -303,24 +318,22 @@ cleanup:
 static void
 test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi_opts *opts)
 {
-	struct child *child;
+	static struct child child;
 
 	/* no pid filter */
 	__test_attach_api(binary, pattern, opts, NULL);
 
 	/* pid filter */
-	child = spawn_child();
-	if (!ASSERT_OK_PTR(child, "spawn_child"))
+	if (!ASSERT_OK(spawn_child(&child), "spawn_child"))
 		return;
 
-	__test_attach_api(binary, pattern, opts, child);
+	__test_attach_api(binary, pattern, opts, &child);
 
 	/* pid filter (thread) */
-	child = spawn_thread();
-	if (!ASSERT_OK_PTR(child, "spawn_thread"))
+	if (!ASSERT_OK(spawn_thread(&child), "spawn_thread"))
 		return;
 
-	__test_attach_api(binary, pattern, opts, child);
+	__test_attach_api(binary, pattern, opts, &child);
 }
 
 static void test_attach_api_pattern(void)
@@ -516,6 +529,122 @@ cleanup:
 	uprobe_multi__destroy(skel);
 }
 
+#ifdef __x86_64__
+noinline void uprobe_multi_error_func(void)
+{
+	/*
+	 * If --fcf-protection=branch is enabled the gcc generates endbr as
+	 * first instruction, so marking the exact address of int3 with the
+	 * symbol to be used in the attach_uprobe_fail_trap test below.
+	 */
+	asm volatile (
+		".globl uprobe_multi_error_func_int3;	\n"
+		"uprobe_multi_error_func_int3:		\n"
+		"int3					\n"
+	);
+}
+
+/*
+ * Attaching uprobe on uprobe_multi_error_func results in error
+ * because it already starts with int3 instruction.
+ */
+static void attach_uprobe_fail_trap(struct uprobe_multi *skel)
+{
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
+	const char *syms[4] = {
+		"uprobe_multi_func_1",
+		"uprobe_multi_func_2",
+		"uprobe_multi_func_3",
+		"uprobe_multi_error_func_int3",
+	};
+
+	opts.syms = syms;
+	opts.cnt = ARRAY_SIZE(syms);
+
+	skel->links.uprobe = bpf_program__attach_uprobe_multi(skel->progs.uprobe, -1,
+							      "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_ERR_PTR(skel->links.uprobe, "bpf_program__attach_uprobe_multi")) {
+		bpf_link__destroy(skel->links.uprobe);
+		skel->links.uprobe = NULL;
+	}
+}
+#else
+static void attach_uprobe_fail_trap(struct uprobe_multi *skel) { }
+#endif
+
+short sema_1 __used, sema_2 __used;
+
+static void attach_uprobe_fail_refctr(struct uprobe_multi *skel)
+{
+	unsigned long *tmp_offsets = NULL, *tmp_ref_ctr_offsets = NULL;
+	unsigned long offsets[3], ref_ctr_offsets[3];
+	LIBBPF_OPTS(bpf_link_create_opts, opts);
+	const char *path = "/proc/self/exe";
+	const char *syms[3] = {
+		"uprobe_multi_func_1",
+		"uprobe_multi_func_2",
+	};
+	const char *sema[3] = {
+		"sema_1",
+		"sema_2",
+	};
+	int prog_fd, link_fd, err;
+
+	prog_fd = bpf_program__fd(skel->progs.uprobe_extra);
+
+	err = elf_resolve_syms_offsets("/proc/self/exe", 2, (const char **) &syms,
+				       &tmp_offsets, STT_FUNC);
+	if (!ASSERT_OK(err, "elf_resolve_syms_offsets_func"))
+		return;
+
+	err = elf_resolve_syms_offsets("/proc/self/exe", 2, (const char **) &sema,
+				       &tmp_ref_ctr_offsets, STT_OBJECT);
+	if (!ASSERT_OK(err, "elf_resolve_syms_offsets_sema"))
+		goto cleanup;
+
+	/*
+	 * We attach to 3 uprobes on 2 functions, so 2 uprobes share single function,
+	 * but with different ref_ctr_offset which is not allowed and results in fail.
+	 */
+	offsets[0] = tmp_offsets[0]; /* uprobe_multi_func_1 */
+	offsets[1] = tmp_offsets[1]; /* uprobe_multi_func_2 */
+	offsets[2] = tmp_offsets[1]; /* uprobe_multi_func_2 */
+
+	ref_ctr_offsets[0] = tmp_ref_ctr_offsets[0]; /* sema_1 */
+	ref_ctr_offsets[1] = tmp_ref_ctr_offsets[1]; /* sema_2 */
+	ref_ctr_offsets[2] = tmp_ref_ctr_offsets[0]; /* sema_1, error */
+
+	opts.uprobe_multi.path = path;
+	opts.uprobe_multi.offsets = (const unsigned long *) &offsets;
+	opts.uprobe_multi.ref_ctr_offsets = (const unsigned long *) &ref_ctr_offsets;
+	opts.uprobe_multi.cnt = 3;
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		close(link_fd);
+
+cleanup:
+	free(tmp_ref_ctr_offsets);
+	free(tmp_offsets);
+}
+
+static void test_attach_uprobe_fails(void)
+{
+	struct uprobe_multi *skel = NULL;
+
+	skel = uprobe_multi__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi__open_and_load"))
+		return;
+
+	/* attach fails due to adding uprobe on trap instruction, x86_64 only */
+	attach_uprobe_fail_trap(skel);
+
+	/* attach fail due to wrong ref_ctr_offs on one of the uprobes */
+	attach_uprobe_fail_refctr(skel);
+
+	uprobe_multi__destroy(skel);
+}
+
 static void __test_link_api(struct child *child)
 {
 	int prog_fd, link1_fd = -1, link2_fd = -1, link3_fd = -1, link4_fd = -1;
@@ -595,24 +724,296 @@ cleanup:
 
 static void test_link_api(void)
 {
-	struct child *child;
+	static struct child child;
 
 	/* no pid filter */
 	__test_link_api(NULL);
 
 	/* pid filter */
-	child = spawn_child();
-	if (!ASSERT_OK_PTR(child, "spawn_child"))
+	if (!ASSERT_OK(spawn_child(&child), "spawn_child"))
 		return;
 
-	__test_link_api(child);
+	__test_link_api(&child);
 
 	/* pid filter (thread) */
-	child = spawn_thread();
-	if (!ASSERT_OK_PTR(child, "spawn_thread"))
+	if (!ASSERT_OK(spawn_thread(&child), "spawn_thread"))
+		return;
+
+	__test_link_api(&child);
+}
+
+static struct bpf_program *
+get_program(struct uprobe_multi_consumers *skel, int prog)
+{
+	switch (prog) {
+	case 0:
+		return skel->progs.uprobe_0;
+	case 1:
+		return skel->progs.uprobe_1;
+	case 2:
+		return skel->progs.uprobe_2;
+	case 3:
+		return skel->progs.uprobe_3;
+	default:
+		ASSERT_FAIL("get_program");
+		return NULL;
+	}
+}
+
+static struct bpf_link **
+get_link(struct uprobe_multi_consumers *skel, int link)
+{
+	switch (link) {
+	case 0:
+		return &skel->links.uprobe_0;
+	case 1:
+		return &skel->links.uprobe_1;
+	case 2:
+		return &skel->links.uprobe_2;
+	case 3:
+		return &skel->links.uprobe_3;
+	default:
+		ASSERT_FAIL("get_link");
+		return NULL;
+	}
+}
+
+static int uprobe_attach(struct uprobe_multi_consumers *skel, int idx)
+{
+	struct bpf_program *prog = get_program(skel, idx);
+	struct bpf_link **link = get_link(skel, idx);
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
+
+	if (!prog || !link)
+		return -1;
+
+	/*
+	 * bit/prog: 0,1 uprobe entry
+	 * bit/prog: 2,3 uprobe return
+	 */
+	opts.retprobe = idx == 2 || idx == 3;
+
+	*link = bpf_program__attach_uprobe_multi(prog, 0, "/proc/self/exe",
+						"uprobe_consumer_test",
+						&opts);
+	if (!ASSERT_OK_PTR(*link, "bpf_program__attach_uprobe_multi"))
+		return -1;
+	return 0;
+}
+
+static void uprobe_detach(struct uprobe_multi_consumers *skel, int idx)
+{
+	struct bpf_link **link = get_link(skel, idx);
+
+	bpf_link__destroy(*link);
+	*link = NULL;
+}
+
+static bool test_bit(int bit, unsigned long val)
+{
+	return val & (1 << bit);
+}
+
+noinline int
+uprobe_consumer_test(struct uprobe_multi_consumers *skel,
+		     unsigned long before, unsigned long after)
+{
+	int idx;
+
+	/* detach uprobe for each unset programs in 'before' state ... */
+	for (idx = 0; idx < 4; idx++) {
+		if (test_bit(idx, before) && !test_bit(idx, after))
+			uprobe_detach(skel, idx);
+	}
+
+	/* ... and attach all new programs in 'after' state */
+	for (idx = 0; idx < 4; idx++) {
+		if (!test_bit(idx, before) && test_bit(idx, after)) {
+			if (!ASSERT_OK(uprobe_attach(skel, idx), "uprobe_attach_after"))
+				return -1;
+		}
+	}
+	return 0;
+}
+
+static void consumer_test(struct uprobe_multi_consumers *skel,
+			  unsigned long before, unsigned long after)
+{
+	int err, idx;
+
+	printf("consumer_test before %lu after %lu\n", before, after);
+
+	/* 'before' is each, we attach uprobe for every set idx */
+	for (idx = 0; idx < 4; idx++) {
+		if (test_bit(idx, before)) {
+			if (!ASSERT_OK(uprobe_attach(skel, idx), "uprobe_attach_before"))
+				goto cleanup;
+		}
+	}
+
+	err = uprobe_consumer_test(skel, before, after);
+	if (!ASSERT_EQ(err, 0, "uprobe_consumer_test"))
+		goto cleanup;
+
+	for (idx = 0; idx < 4; idx++) {
+		const char *fmt = "BUG";
+		__u64 val = 0;
+
+		if (idx < 2) {
+			/*
+			 * uprobe entry
+			 *   +1 if define in 'before'
+			 */
+			if (test_bit(idx, before))
+				val++;
+			fmt = "prog 0/1: uprobe";
+		} else {
+			/*
+			 * uprobe return is tricky ;-)
+			 *
+			 * to trigger uretprobe consumer, the uretprobe needs to be installed,
+			 * which means one of the 'return' uprobes was alive when probe was hit:
+			 *
+			 *   idxs: 2/3 uprobe return in 'installed' mask
+			 *
+			 * in addition if 'after' state removes everything that was installed in
+			 * 'before' state, then uprobe kernel object goes away and return uprobe
+			 * is not installed and we won't hit it even if it's in 'after' state.
+			 */
+			unsigned long had_uretprobes  = before & 0b1100; /* is uretprobe installed */
+			unsigned long probe_preserved = before & after;  /* did uprobe go away */
+
+			if (had_uretprobes && probe_preserved && test_bit(idx, after))
+				val++;
+			fmt = "idx 2/3: uretprobe";
+		}
+
+		ASSERT_EQ(skel->bss->uprobe_result[idx], val, fmt);
+		skel->bss->uprobe_result[idx] = 0;
+	}
+
+cleanup:
+	for (idx = 0; idx < 4; idx++)
+		uprobe_detach(skel, idx);
+}
+
+static void test_consumers(void)
+{
+	struct uprobe_multi_consumers *skel;
+	int before, after;
+
+	skel = uprobe_multi_consumers__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi_consumers__open_and_load"))
+		return;
+
+	/*
+	 * The idea of this test is to try all possible combinations of
+	 * uprobes consumers attached on single function.
+	 *
+	 *  - 2 uprobe entry consumer
+	 *  - 2 uprobe exit consumers
+	 *
+	 * The test uses 4 uprobes attached on single function, but that
+	 * translates into single uprobe with 4 consumers in kernel.
+	 *
+	 * The before/after values present the state of attached consumers
+	 * before and after the probed function:
+	 *
+	 *  bit/prog 0,1 : uprobe entry
+	 *  bit/prog 2,3 : uprobe return
+	 *
+	 * For example for:
+	 *
+	 *   before = 0b0101
+	 *   after  = 0b0110
+	 *
+	 * it means that before we call 'uprobe_consumer_test' we attach
+	 * uprobes defined in 'before' value:
+	 *
+	 *   - bit/prog 0: uprobe entry
+	 *   - bit/prog 2: uprobe return
+	 *
+	 * uprobe_consumer_test is called and inside it we attach and detach
+	 * uprobes based on 'after' value:
+	 *
+	 *   - bit/prog 0: stays untouched
+	 *   - bit/prog 2: uprobe return is detached
+	 *
+	 * uprobe_consumer_test returns and we check counters values increased
+	 * by bpf programs on each uprobe to match the expected count based on
+	 * before/after bits.
+	 */
+
+	for (before = 0; before < 16; before++) {
+		for (after = 0; after < 16; after++)
+			consumer_test(skel, before, after);
+	}
+
+	uprobe_multi_consumers__destroy(skel);
+}
+
+static struct bpf_program *uprobe_multi_program(struct uprobe_multi_pid_filter *skel, int idx)
+{
+	switch (idx) {
+	case 0: return skel->progs.uprobe_multi_0;
+	case 1: return skel->progs.uprobe_multi_1;
+	case 2: return skel->progs.uprobe_multi_2;
+	}
+	return NULL;
+}
+
+#define TASKS 3
+
+static void run_pid_filter(struct uprobe_multi_pid_filter *skel, bool clone_vm, bool retprobe)
+{
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts, .retprobe = retprobe);
+	struct bpf_link *link[TASKS] = {};
+	struct child child[TASKS] = {};
+	int i;
+
+	memset(skel->bss->test, 0, sizeof(skel->bss->test));
+
+	for (i = 0; i < TASKS; i++) {
+		if (!ASSERT_OK(spawn_child_flag(&child[i], clone_vm), "spawn_child"))
+			goto cleanup;
+		skel->bss->pids[i] = child[i].pid;
+	}
+
+	for (i = 0; i < TASKS; i++) {
+		link[i] = bpf_program__attach_uprobe_multi(uprobe_multi_program(skel, i),
+							   child[i].pid, "/proc/self/exe",
+							   "uprobe_multi_func_1", &opts);
+		if (!ASSERT_OK_PTR(link[i], "bpf_program__attach_uprobe_multi"))
+			goto cleanup;
+	}
+
+	for (i = 0; i < TASKS; i++)
+		kick_child(&child[i]);
+
+	for (i = 0; i < TASKS; i++) {
+		ASSERT_EQ(skel->bss->test[i][0], 1, "pid");
+		ASSERT_EQ(skel->bss->test[i][1], 0, "unknown");
+	}
+
+cleanup:
+	for (i = 0; i < TASKS; i++)
+		bpf_link__destroy(link[i]);
+	for (i = 0; i < TASKS; i++)
+		release_child(&child[i]);
+}
+
+static void test_pid_filter_process(bool clone_vm)
+{
+	struct uprobe_multi_pid_filter *skel;
+
+	skel = uprobe_multi_pid_filter__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi_pid_filter__open_and_load"))
 		return;
 
-	__test_link_api(child);
+	run_pid_filter(skel, clone_vm, false);
+	run_pid_filter(skel, clone_vm, true);
+
+	uprobe_multi_pid_filter__destroy(skel);
 }
 
 static void test_bench_attach_uprobe(void)
@@ -703,4 +1104,12 @@ void test_uprobe_multi_test(void)
 		test_bench_attach_usdt();
 	if (test__start_subtest("attach_api_fails"))
 		test_attach_api_fails();
+	if (test__start_subtest("attach_uprobe_fails"))
+		test_attach_uprobe_fails();
+	if (test__start_subtest("consumers"))
+		test_consumers();
+	if (test__start_subtest("filter_fork"))
+		test_pid_filter_process(false);
+	if (test__start_subtest("filter_clone_vm"))
+		test_pid_filter_process(true);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c
index e51721df14fc..d424e7ecbd12 100644
--- a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c
@@ -4,6 +4,7 @@
 #define _GNU_SOURCE
 #include <linux/compiler.h>
 #include <linux/ring_buffer.h>
+#include <linux/build_bug.h>
 #include <pthread.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -642,7 +643,7 @@ static void test_user_ringbuf_blocking_reserve(void)
 	if (!ASSERT_EQ(err, 0, "deferred_kick_thread\n"))
 		goto cleanup;
 
-	/* After spawning another thread that asychronously kicks the kernel to
+	/* After spawning another thread that asynchronously kicks the kernel to
 	 * drain the messages, we're able to block and successfully get a
 	 * sample once we receive an event notification.
 	 */
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index 9dc3687bc406..e26b5150fc43 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -21,6 +21,7 @@
 #include "verifier_cgroup_inv_retcode.skel.h"
 #include "verifier_cgroup_skb.skel.h"
 #include "verifier_cgroup_storage.skel.h"
+#include "verifier_const.skel.h"
 #include "verifier_const_or.skel.h"
 #include "verifier_ctx.skel.h"
 #include "verifier_ctx_sk_msg.skel.h"
@@ -39,6 +40,7 @@
 #include "verifier_int_ptr.skel.h"
 #include "verifier_iterating_callbacks.skel.h"
 #include "verifier_jeq_infer_not_null.skel.h"
+#include "verifier_jit_convergence.skel.h"
 #include "verifier_ld_ind.skel.h"
 #include "verifier_ldsx.skel.h"
 #include "verifier_leak_ptr.skel.h"
@@ -53,6 +55,7 @@
 #include "verifier_movsx.skel.h"
 #include "verifier_netfilter_ctx.skel.h"
 #include "verifier_netfilter_retcode.skel.h"
+#include "verifier_bpf_fastcall.skel.h"
 #include "verifier_or_jmp32_k.skel.h"
 #include "verifier_precision.skel.h"
 #include "verifier_prevent_map_lookup.skel.h"
@@ -74,6 +77,7 @@
 #include "verifier_stack_ptr.skel.h"
 #include "verifier_subprog_precision.skel.h"
 #include "verifier_subreg.skel.h"
+#include "verifier_tailcall_jit.skel.h"
 #include "verifier_typedef.skel.h"
 #include "verifier_uninit.skel.h"
 #include "verifier_unpriv.skel.h"
@@ -84,10 +88,13 @@
 #include "verifier_value_or_null.skel.h"
 #include "verifier_value_ptr_arith.skel.h"
 #include "verifier_var_off.skel.h"
+#include "verifier_vfs_accept.skel.h"
+#include "verifier_vfs_reject.skel.h"
 #include "verifier_xadd.skel.h"
 #include "verifier_xdp.skel.h"
 #include "verifier_xdp_direct_packet_access.skel.h"
 #include "verifier_bits_iter.skel.h"
+#include "verifier_lsm.skel.h"
 
 #define MAX_ENTRIES 11
 
@@ -140,6 +147,7 @@ void test_verifier_cfg(void)                  { RUN(verifier_cfg); }
 void test_verifier_cgroup_inv_retcode(void)   { RUN(verifier_cgroup_inv_retcode); }
 void test_verifier_cgroup_skb(void)           { RUN(verifier_cgroup_skb); }
 void test_verifier_cgroup_storage(void)       { RUN(verifier_cgroup_storage); }
+void test_verifier_const(void)                { RUN(verifier_const); }
 void test_verifier_const_or(void)             { RUN(verifier_const_or); }
 void test_verifier_ctx(void)                  { RUN(verifier_ctx); }
 void test_verifier_ctx_sk_msg(void)           { RUN(verifier_ctx_sk_msg); }
@@ -158,6 +166,7 @@ void test_verifier_helper_value_access(void)  { RUN(verifier_helper_value_access
 void test_verifier_int_ptr(void)              { RUN(verifier_int_ptr); }
 void test_verifier_iterating_callbacks(void)  { RUN(verifier_iterating_callbacks); }
 void test_verifier_jeq_infer_not_null(void)   { RUN(verifier_jeq_infer_not_null); }
+void test_verifier_jit_convergence(void)      { RUN(verifier_jit_convergence); }
 void test_verifier_ld_ind(void)               { RUN(verifier_ld_ind); }
 void test_verifier_ldsx(void)                  { RUN(verifier_ldsx); }
 void test_verifier_leak_ptr(void)             { RUN(verifier_leak_ptr); }
@@ -172,6 +181,7 @@ void test_verifier_meta_access(void)          { RUN(verifier_meta_access); }
 void test_verifier_movsx(void)                 { RUN(verifier_movsx); }
 void test_verifier_netfilter_ctx(void)        { RUN(verifier_netfilter_ctx); }
 void test_verifier_netfilter_retcode(void)    { RUN(verifier_netfilter_retcode); }
+void test_verifier_bpf_fastcall(void)         { RUN(verifier_bpf_fastcall); }
 void test_verifier_or_jmp32_k(void)           { RUN(verifier_or_jmp32_k); }
 void test_verifier_precision(void)            { RUN(verifier_precision); }
 void test_verifier_prevent_map_lookup(void)   { RUN(verifier_prevent_map_lookup); }
@@ -193,6 +203,7 @@ void test_verifier_spin_lock(void)            { RUN(verifier_spin_lock); }
 void test_verifier_stack_ptr(void)            { RUN(verifier_stack_ptr); }
 void test_verifier_subprog_precision(void)    { RUN(verifier_subprog_precision); }
 void test_verifier_subreg(void)               { RUN(verifier_subreg); }
+void test_verifier_tailcall_jit(void)         { RUN(verifier_tailcall_jit); }
 void test_verifier_typedef(void)              { RUN(verifier_typedef); }
 void test_verifier_uninit(void)               { RUN(verifier_uninit); }
 void test_verifier_unpriv(void)               { RUN(verifier_unpriv); }
@@ -202,10 +213,13 @@ void test_verifier_value(void)                { RUN(verifier_value); }
 void test_verifier_value_illegal_alu(void)    { RUN(verifier_value_illegal_alu); }
 void test_verifier_value_or_null(void)        { RUN(verifier_value_or_null); }
 void test_verifier_var_off(void)              { RUN(verifier_var_off); }
+void test_verifier_vfs_accept(void)	      { RUN(verifier_vfs_accept); }
+void test_verifier_vfs_reject(void)	      { RUN(verifier_vfs_reject); }
 void test_verifier_xadd(void)                 { RUN(verifier_xadd); }
 void test_verifier_xdp(void)                  { RUN(verifier_xdp); }
 void test_verifier_xdp_direct_packet_access(void) { RUN(verifier_xdp_direct_packet_access); }
 void test_verifier_bits_iter(void) { RUN(verifier_bits_iter); }
+void test_verifier_lsm(void)                  { RUN(verifier_lsm); }
 
 static int init_test_val_map(struct bpf_object *obj, char *map_name)
 {
diff --git a/tools/testing/selftests/bpf/progs/arena_atomics.c b/tools/testing/selftests/bpf/progs/arena_atomics.c
index bb0acd79d28a..40dd57fca5cc 100644
--- a/tools/testing/selftests/bpf/progs/arena_atomics.c
+++ b/tools/testing/selftests/bpf/progs/arena_atomics.c
@@ -4,6 +4,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include <stdbool.h>
+#include <stdatomic.h>
 #include "bpf_arena_common.h"
 
 struct {
@@ -77,8 +78,13 @@ int sub(const void *ctx)
 	return 0;
 }
 
+#ifdef __BPF_FEATURE_ATOMIC_MEM_ORDERING
+_Atomic __u64 __arena_global and64_value = (0x110ull << 32);
+_Atomic __u32 __arena_global and32_value = 0x110;
+#else
 __u64 __arena_global and64_value = (0x110ull << 32);
 __u32 __arena_global and32_value = 0x110;
+#endif
 
 SEC("raw_tp/sys_enter")
 int and(const void *ctx)
@@ -86,16 +92,25 @@ int and(const void *ctx)
 	if (pid != (bpf_get_current_pid_tgid() >> 32))
 		return 0;
 #ifdef ENABLE_ATOMICS_TESTS
-
+#ifdef __BPF_FEATURE_ATOMIC_MEM_ORDERING
+	__c11_atomic_fetch_and(&and64_value, 0x011ull << 32, memory_order_relaxed);
+	__c11_atomic_fetch_and(&and32_value, 0x011, memory_order_relaxed);
+#else
 	__sync_fetch_and_and(&and64_value, 0x011ull << 32);
 	__sync_fetch_and_and(&and32_value, 0x011);
 #endif
+#endif
 
 	return 0;
 }
 
+#ifdef __BPF_FEATURE_ATOMIC_MEM_ORDERING
+_Atomic __u32 __arena_global or32_value = 0x110;
+_Atomic __u64 __arena_global or64_value = (0x110ull << 32);
+#else
 __u32 __arena_global or32_value = 0x110;
 __u64 __arena_global or64_value = (0x110ull << 32);
+#endif
 
 SEC("raw_tp/sys_enter")
 int or(const void *ctx)
@@ -103,15 +118,25 @@ int or(const void *ctx)
 	if (pid != (bpf_get_current_pid_tgid() >> 32))
 		return 0;
 #ifdef ENABLE_ATOMICS_TESTS
+#ifdef __BPF_FEATURE_ATOMIC_MEM_ORDERING
+	__c11_atomic_fetch_or(&or64_value, 0x011ull << 32, memory_order_relaxed);
+	__c11_atomic_fetch_or(&or32_value, 0x011, memory_order_relaxed);
+#else
 	__sync_fetch_and_or(&or64_value, 0x011ull << 32);
 	__sync_fetch_and_or(&or32_value, 0x011);
 #endif
+#endif
 
 	return 0;
 }
 
+#ifdef __BPF_FEATURE_ATOMIC_MEM_ORDERING
+_Atomic __u64 __arena_global xor64_value = (0x110ull << 32);
+_Atomic __u32 __arena_global xor32_value = 0x110;
+#else
 __u64 __arena_global xor64_value = (0x110ull << 32);
 __u32 __arena_global xor32_value = 0x110;
+#endif
 
 SEC("raw_tp/sys_enter")
 int xor(const void *ctx)
@@ -119,9 +144,14 @@ int xor(const void *ctx)
 	if (pid != (bpf_get_current_pid_tgid() >> 32))
 		return 0;
 #ifdef ENABLE_ATOMICS_TESTS
+#ifdef __BPF_FEATURE_ATOMIC_MEM_ORDERING
+	__c11_atomic_fetch_xor(&xor64_value, 0x011ull << 32, memory_order_relaxed);
+	__c11_atomic_fetch_xor(&xor32_value, 0x011, memory_order_relaxed);
+#else
 	__sync_fetch_and_xor(&xor64_value, 0x011ull << 32);
 	__sync_fetch_and_xor(&xor32_value, 0x011);
 #endif
+#endif
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c
index d665b8a15cc4..f089faa97ae6 100644
--- a/tools/testing/selftests/bpf/progs/bpf_cubic.c
+++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
-/* WARNING: This implemenation is not necessarily the same
+/* WARNING: This implementation is not necessarily the same
  * as the tcp_cubic.c.  The purpose is mainly for testing
  * the kernel BPF logic.
  *
@@ -314,7 +314,7 @@ static void bictcp_update(struct bpf_bictcp *ca, __u32 cwnd, __u32 acked)
 	 * (so time^3 is done by using 64 bit)
 	 * and without the support of division of 64bit numbers
 	 * (so all divisions are done by using 32 bit)
-	 *  also NOTE the unit of those veriables
+	 *  also NOTE the unit of those variables
 	 *	  time  = (t - K) / 2^bictcp_HZ
 	 *	  c = bic_scale >> 10
 	 * rtt  = (srtt >> 3) / HZ
@@ -507,7 +507,7 @@ void BPF_PROG(bpf_cubic_acked, struct sock *sk, const struct ack_sample *sample)
 	__u32 delay;
 
 	bpf_cubic_acked_called = 1;
-	/* Some calls are for duplicates without timetamps */
+	/* Some calls are for duplicates without timestamps */
 	if (sample->rtt_us < 0)
 		return;
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
index 02f552e7fd4d..7cd73e75f52a 100644
--- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c
+++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
@@ -26,7 +26,7 @@ static bool before(__u32 seq1, __u32 seq2)
 
 char _license[] SEC("license") = "GPL";
 
-volatile const char fallback[TCP_CA_NAME_MAX];
+volatile const char fallback_cc[TCP_CA_NAME_MAX];
 const char bpf_dctcp[] = "bpf_dctcp";
 const char tcp_cdg[] = "cdg";
 char cc_res[TCP_CA_NAME_MAX];
@@ -71,10 +71,10 @@ void BPF_PROG(bpf_dctcp_init, struct sock *sk)
 	struct bpf_dctcp *ca = inet_csk_ca(sk);
 	int *stg;
 
-	if (!(tp->ecn_flags & TCP_ECN_OK) && fallback[0]) {
+	if (!(tp->ecn_flags & TCP_ECN_OK) && fallback_cc[0]) {
 		/* Switch to fallback */
 		if (bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION,
-				   (void *)fallback, sizeof(fallback)) == -EBUSY)
+				   (void *)fallback_cc, sizeof(fallback_cc)) == -EBUSY)
 			ebusy_cnt++;
 
 		/* Switch back to myself and the recurred bpf_dctcp_init()
@@ -87,7 +87,7 @@ void BPF_PROG(bpf_dctcp_init, struct sock *sk)
 
 		/* Switch back to fallback */
 		if (bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION,
-				   (void *)fallback, sizeof(fallback)) == -EBUSY)
+				   (void *)fallback_cc, sizeof(fallback_cc)) == -EBUSY)
 			ebusy_cnt++;
 
 		/* Expecting -ENOTSUPP for tcp_cdg_res */
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index 81097a3f15eb..eccaf955e394 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -2,6 +2,9 @@
 #ifndef __BPF_MISC_H__
 #define __BPF_MISC_H__
 
+#define XSTR(s) STR(s)
+#define STR(s) #s
+
 /* This set of attributes controls behavior of the
  * test_loader.c:test_loader__run_subtests().
  *
@@ -22,10 +25,49 @@
  *
  * __msg             Message expected to be found in the verifier log.
  *                   Multiple __msg attributes could be specified.
+ *                   To match a regular expression use "{{" "}}" brackets,
+ *                   e.g. "foo{{[0-9]+}}"  matches strings like "foo007".
+ *                   Extended POSIX regular expression syntax is allowed
+ *                   inside the brackets.
  * __msg_unpriv      Same as __msg but for unprivileged mode.
  *
- * __regex           Same as __msg, but using a regular expression.
- * __regex_unpriv    Same as __msg_unpriv but using a regular expression.
+ * __xlated          Expect a line in a disassembly log after verifier applies rewrites.
+ *                   Multiple __xlated attributes could be specified.
+ *                   Regular expressions could be specified same way as in __msg.
+ * __xlated_unpriv   Same as __xlated but for unprivileged mode.
+ *
+ * __jited           Match a line in a disassembly of the jited BPF program.
+ *                   Has to be used after __arch_* macro.
+ *                   For example:
+ *
+ *                       __arch_x86_64
+ *                       __jited("   endbr64")
+ *                       __jited("   nopl    (%rax,%rax)")
+ *                       __jited("   xorq    %rax, %rax")
+ *                       ...
+ *                       __naked void some_test(void)
+ *                       {
+ *                           asm volatile (... ::: __clobber_all);
+ *                       }
+ *
+ *                   Regular expressions could be included in patterns same way
+ *                   as in __msg.
+ *
+ *                   By default assume that each pattern has to be matched on the
+ *                   next consecutive line of disassembly, e.g.:
+ *
+ *                       __jited("   endbr64")             # matched on line N
+ *                       __jited("   nopl    (%rax,%rax)") # matched on line N+1
+ *
+ *                   If match occurs on a wrong line an error is reported.
+ *                   To override this behaviour use literal "...", e.g.:
+ *
+ *                       __jited("   endbr64")             # matched on line N
+ *                       __jited("...")                    # not matched
+ *                       __jited("   nopl    (%rax,%rax)") # matched on any line >= N
+ *
+ * __jited_unpriv    Same as __jited but for unprivileged mode.
+ *
  *
  * __success         Expect program load success in privileged mode.
  * __success_unpriv  Expect program load success in unprivileged mode.
@@ -60,14 +102,20 @@
  * __auxiliary         Annotated program is not a separate test, but used as auxiliary
  *                     for some other test cases and should always be loaded.
  * __auxiliary_unpriv  Same, but load program in unprivileged mode.
+ *
+ * __arch_*          Specify on which architecture the test case should be tested.
+ *                   Several __arch_* annotations could be specified at once.
+ *                   When test case is not run on current arch it is marked as skipped.
  */
-#define __msg(msg)		__attribute__((btf_decl_tag("comment:test_expect_msg=" msg)))
-#define __regex(regex)		__attribute__((btf_decl_tag("comment:test_expect_regex=" regex)))
+#define __msg(msg)		__attribute__((btf_decl_tag("comment:test_expect_msg=" XSTR(__COUNTER__) "=" msg)))
+#define __xlated(msg)		__attribute__((btf_decl_tag("comment:test_expect_xlated=" XSTR(__COUNTER__) "=" msg)))
+#define __jited(msg)		__attribute__((btf_decl_tag("comment:test_jited=" XSTR(__COUNTER__) "=" msg)))
 #define __failure		__attribute__((btf_decl_tag("comment:test_expect_failure")))
 #define __success		__attribute__((btf_decl_tag("comment:test_expect_success")))
 #define __description(desc)	__attribute__((btf_decl_tag("comment:test_description=" desc)))
-#define __msg_unpriv(msg)	__attribute__((btf_decl_tag("comment:test_expect_msg_unpriv=" msg)))
-#define __regex_unpriv(regex)	__attribute__((btf_decl_tag("comment:test_expect_regex_unpriv=" regex)))
+#define __msg_unpriv(msg)	__attribute__((btf_decl_tag("comment:test_expect_msg_unpriv=" XSTR(__COUNTER__) "=" msg)))
+#define __xlated_unpriv(msg)	__attribute__((btf_decl_tag("comment:test_expect_xlated_unpriv=" XSTR(__COUNTER__) "=" msg)))
+#define __jited_unpriv(msg)	__attribute__((btf_decl_tag("comment:test_jited=" XSTR(__COUNTER__) "=" msg)))
 #define __failure_unpriv	__attribute__((btf_decl_tag("comment:test_expect_failure_unpriv")))
 #define __success_unpriv	__attribute__((btf_decl_tag("comment:test_expect_success_unpriv")))
 #define __log_level(lvl)	__attribute__((btf_decl_tag("comment:test_log_level="#lvl)))
@@ -77,6 +125,10 @@
 #define __auxiliary		__attribute__((btf_decl_tag("comment:test_auxiliary")))
 #define __auxiliary_unpriv	__attribute__((btf_decl_tag("comment:test_auxiliary_unpriv")))
 #define __btf_path(path)	__attribute__((btf_decl_tag("comment:test_btf_path=" path)))
+#define __arch(arch)		__attribute__((btf_decl_tag("comment:test_arch=" arch)))
+#define __arch_x86_64		__arch("X86_64")
+#define __arch_arm64		__arch("ARM64")
+#define __arch_riscv64		__arch("RISCV64")
 
 /* Convenience macro for use with 'asm volatile' blocks */
 #define __naked __attribute__((naked))
diff --git a/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c b/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c
index 1a476d8ed354..9e7d9674ce2a 100644
--- a/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c
+++ b/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c
@@ -43,9 +43,7 @@ int BPF_KPROBE(handle_sys_prctl)
 
 	/* test for PT_REGS_PARM */
 
-#if !defined(bpf_target_arm64) && !defined(bpf_target_s390)
 	bpf_probe_read_kernel(&tmp, sizeof(tmp), &PT_REGS_PARM1_SYSCALL(real_regs));
-#endif
 	arg1 = tmp;
 	bpf_probe_read_kernel(&arg2, sizeof(arg2), &PT_REGS_PARM2_SYSCALL(real_regs));
 	bpf_probe_read_kernel(&arg3, sizeof(arg3), &PT_REGS_PARM3_SYSCALL(real_regs));
diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi.h b/tools/testing/selftests/bpf/progs/cg_storage_multi.h
index a0778fe7857a..41d59f0ee606 100644
--- a/tools/testing/selftests/bpf/progs/cg_storage_multi.h
+++ b/tools/testing/selftests/bpf/progs/cg_storage_multi.h
@@ -3,8 +3,6 @@
 #ifndef __PROGS_CG_STORAGE_MULTI_H
 #define __PROGS_CG_STORAGE_MULTI_H
 
-#include <asm/types.h>
-
 struct cgroup_value {
 	__u32 egress_pkts;
 	__u32 ingress_pkts;
diff --git a/tools/testing/selftests/bpf/progs/cgroup_ancestor.c b/tools/testing/selftests/bpf/progs/cgroup_ancestor.c
new file mode 100644
index 000000000000..8c2deb4fc493
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cgroup_ancestor.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_tracing_net.h"
+#define NUM_CGROUP_LEVELS	4
+
+__u64 cgroup_ids[NUM_CGROUP_LEVELS];
+__u16 dport;
+
+static __always_inline void log_nth_level(struct __sk_buff *skb, __u32 level)
+{
+	/* [1] &level passed to external function that may change it, it's
+	 *     incompatible with loop unroll.
+	 */
+	cgroup_ids[level] = bpf_skb_ancestor_cgroup_id(skb, level);
+}
+
+SEC("tc")
+int log_cgroup_id(struct __sk_buff *skb)
+{
+	struct sock *sk = (void *)skb->sk;
+
+	if (!sk)
+		return TC_ACT_OK;
+
+	sk = bpf_core_cast(sk, struct sock);
+	if (sk->sk_protocol == IPPROTO_UDP && sk->sk_dport == dport) {
+		log_nth_level(skb, 0);
+		log_nth_level(skb, 1);
+		log_nth_level(skb, 2);
+		log_nth_level(skb, 3);
+	}
+
+	return TC_ACT_OK;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/cgroup_storage.c b/tools/testing/selftests/bpf/progs/cgroup_storage.c
new file mode 100644
index 000000000000..db1e4d2d3281
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cgroup_storage.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CGROUP_STORAGE);
+	__type(key, struct bpf_cgroup_storage_key);
+	__type(value, __u64);
+} cgroup_storage SEC(".maps");
+
+SEC("cgroup_skb/egress")
+int bpf_prog(struct __sk_buff *skb)
+{
+	__u64 *counter;
+
+	counter = bpf_get_local_storage(&cgroup_storage, 0);
+	__sync_fetch_and_add(counter, 1);
+
+	/* Drop one out of every two packets */
+	return (*counter & 1);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/dev_cgroup.c b/tools/testing/selftests/bpf/progs/dev_cgroup.c
index 79b54a4fa244..c1dfbd2b56fc 100644
--- a/tools/testing/selftests/bpf/progs/dev_cgroup.c
+++ b/tools/testing/selftests/bpf/progs/dev_cgroup.c
@@ -41,14 +41,14 @@ int bpf_prog1(struct bpf_cgroup_dev_ctx *ctx)
 	bpf_trace_printk(fmt, sizeof(fmt), ctx->major, ctx->minor);
 #endif
 
-	/* Allow access to /dev/zero and /dev/random.
+	/* Allow access to /dev/null and /dev/urandom.
 	 * Forbid everything else.
 	 */
 	if (ctx->major != 1 || type != BPF_DEVCG_DEV_CHAR)
 		return 0;
 
 	switch (ctx->minor) {
-	case 5: /* 1:5 /dev/zero */
+	case 3: /* 1:3 /dev/null */
 	case 9: /* 1:9 /dev/urandom */
 		return 1;
 	}
diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c
index c3bc186af21e..8f36c9de7591 100644
--- a/tools/testing/selftests/bpf/progs/dynptr_fail.c
+++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c
@@ -965,7 +965,7 @@ int dynptr_invalidate_slice_reinit(void *ctx)
  * mem_or_null pointers.
  */
 SEC("?raw_tp")
-__failure __regex("R[0-9]+ type=scalar expected=percpu_ptr_")
+__failure __msg("R{{[0-9]+}} type=scalar expected=percpu_ptr_")
 int dynptr_invalidate_slice_or_null(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -983,7 +983,7 @@ int dynptr_invalidate_slice_or_null(void *ctx)
 
 /* Destruction of dynptr should also any slices obtained from it */
 SEC("?raw_tp")
-__failure __regex("R[0-9]+ invalid mem access 'scalar'")
+__failure __msg("R{{[0-9]+}} invalid mem access 'scalar'")
 int dynptr_invalidate_slice_failure(void *ctx)
 {
 	struct bpf_dynptr ptr1;
@@ -1070,7 +1070,7 @@ int dynptr_read_into_slot(void *ctx)
 
 /* bpf_dynptr_slice()s are read-only and cannot be written to */
 SEC("?tc")
-__failure __regex("R[0-9]+ cannot write into rdonly_mem")
+__failure __msg("R{{[0-9]+}} cannot write into rdonly_mem")
 int skb_invalid_slice_write(struct __sk_buff *skb)
 {
 	struct bpf_dynptr ptr;
diff --git a/tools/testing/selftests/bpf/progs/epilogue_exit.c b/tools/testing/selftests/bpf/progs/epilogue_exit.c
new file mode 100644
index 000000000000..33d3a57bee90
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/epilogue_exit.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../bpf_testmod/bpf_testmod.h"
+#include "../bpf_testmod/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+__success
+/* save __u64 *ctx to stack */
+__xlated("0: *(u64 *)(r10 -8) = r1")
+/* main prog */
+__xlated("1: r1 = *(u64 *)(r1 +0)")
+__xlated("2: r2 = *(u64 *)(r1 +0)")
+__xlated("3: r3 = 0")
+__xlated("4: r4 = 1")
+__xlated("5: if r2 == 0x0 goto pc+10")
+__xlated("6: r0 = 0")
+__xlated("7: *(u64 *)(r1 +0) = r3")
+/* epilogue */
+__xlated("8: r1 = *(u64 *)(r10 -8)")
+__xlated("9: r1 = *(u64 *)(r1 +0)")
+__xlated("10: r6 = *(u64 *)(r1 +0)")
+__xlated("11: r6 += 10000")
+__xlated("12: *(u64 *)(r1 +0) = r6")
+__xlated("13: r0 = r6")
+__xlated("14: r0 *= 2")
+__xlated("15: exit")
+/* 2nd part of the main prog after the first exit */
+__xlated("16: *(u64 *)(r1 +0) = r4")
+__xlated("17: r0 = 1")
+/* Clear the r1 to ensure it does not have
+ * off-by-1 error and ensure it jumps back to the
+ * beginning of epilogue which initializes
+ * the r1 with the ctx ptr.
+ */
+__xlated("18: r1 = 0")
+__xlated("19: gotol pc-12")
+SEC("struct_ops/test_epilogue_exit")
+__naked int test_epilogue_exit(void)
+{
+	asm volatile (
+	"r1 = *(u64 *)(r1 +0);"
+	"r2 = *(u64 *)(r1 +0);"
+	"r3 = 0;"
+	"r4 = 1;"
+	"if r2 == 0 goto +3;"
+	"r0 = 0;"
+	"*(u64 *)(r1 + 0) = r3;"
+	"exit;"
+	"*(u64 *)(r1 + 0) = r4;"
+	"r0 = 1;"
+	"r1 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_st_ops epilogue_exit = {
+	.test_epilogue = (void *)test_epilogue_exit,
+};
+
+SEC("syscall")
+__retval(20000)
+int syscall_epilogue_exit0(void *ctx)
+{
+	struct st_ops_args args = { .a = 1 };
+
+	return bpf_kfunc_st_ops_test_epilogue(&args);
+}
+
+SEC("syscall")
+__retval(20002)
+int syscall_epilogue_exit1(void *ctx)
+{
+	struct st_ops_args args = {};
+
+	return bpf_kfunc_st_ops_test_epilogue(&args);
+}
diff --git a/tools/testing/selftests/bpf/progs/epilogue_tailcall.c b/tools/testing/selftests/bpf/progs/epilogue_tailcall.c
new file mode 100644
index 000000000000..7275dd594de0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/epilogue_tailcall.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../bpf_testmod/bpf_testmod.h"
+#include "../bpf_testmod/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+static __noinline __used int subprog(struct st_ops_args *args)
+{
+	args->a += 1;
+	return args->a;
+}
+
+SEC("struct_ops/test_epilogue_subprog")
+int BPF_PROG(test_epilogue_subprog, struct st_ops_args *args)
+{
+	subprog(args);
+	return args->a;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+	__array(values, void (void));
+} epilogue_map SEC(".maps") = {
+	.values = {
+		[0] = (void *)&test_epilogue_subprog,
+	}
+};
+
+SEC("struct_ops/test_epilogue_tailcall")
+int test_epilogue_tailcall(unsigned long long *ctx)
+{
+	bpf_tail_call(ctx, &epilogue_map, 0);
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_st_ops epilogue_tailcall = {
+	.test_epilogue = (void *)test_epilogue_tailcall,
+};
+
+SEC(".struct_ops.link")
+struct bpf_testmod_st_ops epilogue_subprog = {
+	.test_epilogue = (void *)test_epilogue_subprog,
+};
+
+SEC("syscall")
+int syscall_epilogue_tailcall(struct st_ops_args *args)
+{
+	return bpf_kfunc_st_ops_test_epilogue(args);
+}
diff --git a/tools/testing/selftests/bpf/progs/err.h b/tools/testing/selftests/bpf/progs/err.h
index d66d283d9e59..38529779a236 100644
--- a/tools/testing/selftests/bpf/progs/err.h
+++ b/tools/testing/selftests/bpf/progs/err.h
@@ -5,6 +5,16 @@
 #define MAX_ERRNO 4095
 #define IS_ERR_VALUE(x) (unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO
 
+#define __STR(x) #x
+
+#define set_if_not_errno_or_zero(x, y)			\
+({							\
+	asm volatile ("if %0 s< -4095 goto +1\n"	\
+		      "if %0 s<= 0 goto +1\n"		\
+		      "%0 = " __STR(y) "\n"		\
+		      : "+r"(x));			\
+})
+
 static inline int IS_ERR_OR_NULL(const void *ptr)
 {
 	return !ptr || IS_ERR_VALUE((unsigned long)ptr);
diff --git a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
index 68587b1de34e..30fd504856c7 100644
--- a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
+++ b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
@@ -4,34 +4,16 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, 1);
-	__type(key, __u32);
-	__type(value, __u64);
-} cg_ids SEC(".maps");
-
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, 1);
-	__type(key, __u32);
-	__type(value, __u32);
-} pidmap SEC(".maps");
+__u64 cg_id;
+__u64 expected_pid;
 
 SEC("tracepoint/syscalls/sys_enter_nanosleep")
 int trace(void *ctx)
 {
 	__u32 pid = bpf_get_current_pid_tgid();
-	__u32 key = 0, *expected_pid;
-	__u64 *val;
-
-	expected_pid = bpf_map_lookup_elem(&pidmap, &key);
-	if (!expected_pid || *expected_pid != pid)
-		return 0;
 
-	val = bpf_map_lookup_elem(&cg_ids, &key);
-	if (val)
-		*val = bpf_get_current_cgroup_id();
+	if (expected_pid == pid)
+		cg_id = bpf_get_current_cgroup_id();
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/iters_testmod.c b/tools/testing/selftests/bpf/progs/iters_testmod.c
new file mode 100644
index 000000000000..df1d3db60b1b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/iters_testmod.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include "bpf_experimental.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "../bpf_testmod/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("raw_tp/sys_enter")
+__success
+int iter_next_trusted(const void *ctx)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct bpf_iter_task_vma vma_it;
+	struct vm_area_struct *vma_ptr;
+
+	bpf_iter_task_vma_new(&vma_it, cur_task, 0);
+
+	vma_ptr = bpf_iter_task_vma_next(&vma_it);
+	if (vma_ptr == NULL)
+		goto out;
+
+	bpf_kfunc_trusted_vma_test(vma_ptr);
+out:
+	bpf_iter_task_vma_destroy(&vma_it);
+	return 0;
+}
+
+SEC("raw_tp/sys_enter")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+int iter_next_trusted_or_null(const void *ctx)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct bpf_iter_task_vma vma_it;
+	struct vm_area_struct *vma_ptr;
+
+	bpf_iter_task_vma_new(&vma_it, cur_task, 0);
+
+	vma_ptr = bpf_iter_task_vma_next(&vma_it);
+
+	bpf_kfunc_trusted_vma_test(vma_ptr);
+
+	bpf_iter_task_vma_destroy(&vma_it);
+	return 0;
+}
+
+SEC("raw_tp/sys_enter")
+__success
+int iter_next_rcu(const void *ctx)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct bpf_iter_task task_it;
+	struct task_struct *task_ptr;
+
+	bpf_iter_task_new(&task_it, cur_task, 0);
+
+	task_ptr = bpf_iter_task_next(&task_it);
+	if (task_ptr == NULL)
+		goto out;
+
+	bpf_kfunc_rcu_task_test(task_ptr);
+out:
+	bpf_iter_task_destroy(&task_it);
+	return 0;
+}
+
+SEC("raw_tp/sys_enter")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+int iter_next_rcu_or_null(const void *ctx)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct bpf_iter_task task_it;
+	struct task_struct *task_ptr;
+
+	bpf_iter_task_new(&task_it, cur_task, 0);
+
+	task_ptr = bpf_iter_task_next(&task_it);
+
+	bpf_kfunc_rcu_task_test(task_ptr);
+
+	bpf_iter_task_destroy(&task_it);
+	return 0;
+}
+
+SEC("raw_tp/sys_enter")
+__failure __msg("R1 must be referenced or trusted")
+int iter_next_rcu_not_trusted(const void *ctx)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct bpf_iter_task task_it;
+	struct task_struct *task_ptr;
+
+	bpf_iter_task_new(&task_it, cur_task, 0);
+
+	task_ptr = bpf_iter_task_next(&task_it);
+	if (task_ptr == NULL)
+		goto out;
+
+	bpf_kfunc_trusted_task_test(task_ptr);
+out:
+	bpf_iter_task_destroy(&task_it);
+	return 0;
+}
+
+SEC("raw_tp/sys_enter")
+__failure __msg("R1 cannot write into rdonly_mem")
+/* Message should not be 'R1 cannot write into rdonly_trusted_mem' */
+int iter_next_ptr_mem_not_trusted(const void *ctx)
+{
+	struct bpf_iter_num num_it;
+	int *num_ptr;
+
+	bpf_iter_num_new(&num_it, 0, 10);
+
+	num_ptr = bpf_iter_num_next(&num_it);
+	if (num_ptr == NULL)
+		goto out;
+
+	bpf_kfunc_trusted_num_test(num_ptr);
+out:
+	bpf_iter_num_destroy(&num_it);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c
index 3873fb6c292a..4a176e6aede8 100644
--- a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c
+++ b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c
@@ -12,6 +12,7 @@ struct bpf_iter_testmod_seq {
 
 extern int bpf_iter_testmod_seq_new(struct bpf_iter_testmod_seq *it, s64 value, int cnt) __ksym;
 extern s64 *bpf_iter_testmod_seq_next(struct bpf_iter_testmod_seq *it) __ksym;
+extern s64 bpf_iter_testmod_seq_value(int blah, struct bpf_iter_testmod_seq *it) __ksym;
 extern void bpf_iter_testmod_seq_destroy(struct bpf_iter_testmod_seq *it) __ksym;
 
 const volatile __s64 exp_empty = 0 + 1;
@@ -76,4 +77,53 @@ int testmod_seq_truncated(const void *ctx)
 	return 0;
 }
 
+SEC("?raw_tp")
+__failure
+__msg("expected an initialized iter_testmod_seq as arg #2")
+int testmod_seq_getter_before_bad(const void *ctx)
+{
+	struct bpf_iter_testmod_seq it;
+
+	return bpf_iter_testmod_seq_value(0, &it);
+}
+
+SEC("?raw_tp")
+__failure
+__msg("expected an initialized iter_testmod_seq as arg #2")
+int testmod_seq_getter_after_bad(const void *ctx)
+{
+	struct bpf_iter_testmod_seq it;
+	s64 sum = 0, *v;
+
+	bpf_iter_testmod_seq_new(&it, 100, 100);
+
+	while ((v = bpf_iter_testmod_seq_next(&it))) {
+		sum += *v;
+	}
+
+	bpf_iter_testmod_seq_destroy(&it);
+
+	return sum + bpf_iter_testmod_seq_value(0, &it);
+}
+
+SEC("?socket")
+__success __retval(1000000)
+int testmod_seq_getter_good(const void *ctx)
+{
+	struct bpf_iter_testmod_seq it;
+	s64 sum = 0, *v;
+
+	bpf_iter_testmod_seq_new(&it, 100, 100);
+
+	while ((v = bpf_iter_testmod_seq_next(&it))) {
+		sum += *v;
+	}
+
+	sum *= bpf_iter_testmod_seq_value(0, &it);
+
+	bpf_iter_testmod_seq_destroy(&it);
+
+	return sum;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c
index 4b0b7b79cdfb..08fae306539c 100644
--- a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c
+++ b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c
@@ -150,4 +150,11 @@ int kfunc_call_test_mem_acquire_fail(struct __sk_buff *skb)
 	return ret;
 }
 
+SEC("?tc")
+int kfunc_call_test_pointer_arg_type_mismatch(struct __sk_buff *skb)
+{
+	bpf_kfunc_call_test_pass_ctx((void *)10);
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash.c b/tools/testing/selftests/bpf/progs/local_kptr_stash.c
index 75043ffc5dad..b092a72b2c9d 100644
--- a/tools/testing/selftests/bpf/progs/local_kptr_stash.c
+++ b/tools/testing/selftests/bpf/progs/local_kptr_stash.c
@@ -8,9 +8,12 @@
 #include "../bpf_experimental.h"
 #include "../bpf_testmod/bpf_testmod_kfunc.h"
 
+struct plain_local;
+
 struct node_data {
 	long key;
 	long data;
+	struct plain_local __kptr * stashed_in_local_kptr;
 	struct bpf_rb_node node;
 };
 
@@ -85,6 +88,7 @@ static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
 
 static int create_and_stash(int idx, int val)
 {
+	struct plain_local *inner_local_kptr;
 	struct map_value *mapval;
 	struct node_data *res;
 
@@ -92,11 +96,25 @@ static int create_and_stash(int idx, int val)
 	if (!mapval)
 		return 1;
 
+	inner_local_kptr = bpf_obj_new(typeof(*inner_local_kptr));
+	if (!inner_local_kptr)
+		return 2;
+
 	res = bpf_obj_new(typeof(*res));
-	if (!res)
-		return 1;
+	if (!res) {
+		bpf_obj_drop(inner_local_kptr);
+		return 3;
+	}
 	res->key = val;
 
+	inner_local_kptr = bpf_kptr_xchg(&res->stashed_in_local_kptr, inner_local_kptr);
+	if (inner_local_kptr) {
+		/* Should never happen, we just obj_new'd res */
+		bpf_obj_drop(inner_local_kptr);
+		bpf_obj_drop(res);
+		return 4;
+	}
+
 	res = bpf_kptr_xchg(&mapval->node, res);
 	if (res)
 		bpf_obj_drop(res);
@@ -169,6 +187,7 @@ long stash_local_with_root(void *ctx)
 SEC("tc")
 long unstash_rb_node(void *ctx)
 {
+	struct plain_local *inner_local_kptr = NULL;
 	struct map_value *mapval;
 	struct node_data *res;
 	long retval;
@@ -180,6 +199,13 @@ long unstash_rb_node(void *ctx)
 
 	res = bpf_kptr_xchg(&mapval->node, NULL);
 	if (res) {
+		inner_local_kptr = bpf_kptr_xchg(&res->stashed_in_local_kptr, inner_local_kptr);
+		if (!inner_local_kptr) {
+			bpf_obj_drop(res);
+			return 1;
+		}
+		bpf_obj_drop(inner_local_kptr);
+
 		retval = res->key;
 		bpf_obj_drop(res);
 		return retval;
diff --git a/tools/testing/selftests/bpf/progs/lsm_tailcall.c b/tools/testing/selftests/bpf/progs/lsm_tailcall.c
new file mode 100644
index 000000000000..49c075ce2d4c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/lsm_tailcall.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Huawei Technologies Co., Ltd */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+SEC("lsm/file_permission")
+int lsm_file_permission_prog(void *ctx)
+{
+	return 0;
+}
+
+SEC("lsm/file_alloc_security")
+int lsm_file_alloc_security_prog(void *ctx)
+{
+	return 0;
+}
+
+SEC("lsm/file_alloc_security")
+int lsm_file_alloc_security_entry(void *ctx)
+{
+	bpf_tail_call_static(ctx, &jmp_table, 0);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/mmap_inner_array.c b/tools/testing/selftests/bpf/progs/mmap_inner_array.c
new file mode 100644
index 000000000000..90aacbc2938a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mmap_inner_array.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct inner_array_type {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__type(key, __u32);
+	__type(value, __u64);
+	__uint(max_entries, 1);
+} inner_array SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__uint(key_size, 4);
+	__uint(value_size, 4);
+	__uint(max_entries, 1);
+	__array(values, struct inner_array_type);
+} outer_map SEC(".maps");
+
+int pid = 0;
+__u64 match_value = 0x13572468;
+bool done = false;
+bool pid_match = false;
+bool outer_map_match = false;
+
+SEC("fentry/" SYS_PREFIX "sys_nanosleep")
+int add_to_list_in_inner_array(void *ctx)
+{
+	__u32 curr_pid, zero = 0;
+	struct bpf_map *map;
+	__u64 *value;
+
+	curr_pid = (u32)bpf_get_current_pid_tgid();
+	if (done || curr_pid != pid)
+		return 0;
+
+	pid_match = true;
+	map = bpf_map_lookup_elem(&outer_map, &curr_pid);
+	if (!map)
+		return 0;
+
+	outer_map_match = true;
+	value = bpf_map_lookup_elem(map, &zero);
+	if (!value)
+		return 0;
+
+	*value = match_value;
+	done = true;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/nested_acquire.c b/tools/testing/selftests/bpf/progs/nested_acquire.c
new file mode 100644
index 000000000000..8e521a21d995
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/nested_acquire.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "../bpf_testmod/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("tp_btf/tcp_probe")
+__success
+int BPF_PROG(test_nested_acquire_nonzero, struct sock *sk, struct sk_buff *skb)
+{
+	struct sk_buff *ptr;
+
+	ptr = bpf_kfunc_nested_acquire_nonzero_offset_test(&sk->sk_write_queue);
+
+	bpf_kfunc_nested_release_test(ptr);
+	return 0;
+}
+
+SEC("tp_btf/tcp_probe")
+__success
+int BPF_PROG(test_nested_acquire_zero, struct sock *sk, struct sk_buff *skb)
+{
+	struct sk_buff *ptr;
+
+	ptr = bpf_kfunc_nested_acquire_zero_offset_test(&sk->__sk_common);
+
+	bpf_kfunc_nested_release_test(ptr);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/pro_epilogue.c b/tools/testing/selftests/bpf/progs/pro_epilogue.c
new file mode 100644
index 000000000000..44bc3f06b4b6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/pro_epilogue.c
@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../bpf_testmod/bpf_testmod.h"
+#include "../bpf_testmod/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+void __kfunc_btf_root(void)
+{
+	bpf_kfunc_st_ops_inc10(NULL);
+}
+
+static __noinline __used int subprog(struct st_ops_args *args)
+{
+	args->a += 1;
+	return args->a;
+}
+
+__success
+/* prologue */
+__xlated("0: r6 = *(u64 *)(r1 +0)")
+__xlated("1: r7 = *(u64 *)(r6 +0)")
+__xlated("2: r7 += 1000")
+__xlated("3: *(u64 *)(r6 +0) = r7")
+/* main prog */
+__xlated("4: r1 = *(u64 *)(r1 +0)")
+__xlated("5: r6 = r1")
+__xlated("6: call kernel-function")
+__xlated("7: r1 = r6")
+__xlated("8: call pc+1")
+__xlated("9: exit")
+SEC("struct_ops/test_prologue")
+__naked int test_prologue(void)
+{
+	asm volatile (
+	"r1 = *(u64 *)(r1 +0);"
+	"r6 = r1;"
+	"call %[bpf_kfunc_st_ops_inc10];"
+	"r1 = r6;"
+	"call subprog;"
+	"exit;"
+	:
+	: __imm(bpf_kfunc_st_ops_inc10)
+	: __clobber_all);
+}
+
+__success
+/* save __u64 *ctx to stack */
+__xlated("0: *(u64 *)(r10 -8) = r1")
+/* main prog */
+__xlated("1: r1 = *(u64 *)(r1 +0)")
+__xlated("2: r6 = r1")
+__xlated("3: call kernel-function")
+__xlated("4: r1 = r6")
+__xlated("5: call pc+")
+/* epilogue */
+__xlated("6: r1 = *(u64 *)(r10 -8)")
+__xlated("7: r1 = *(u64 *)(r1 +0)")
+__xlated("8: r6 = *(u64 *)(r1 +0)")
+__xlated("9: r6 += 10000")
+__xlated("10: *(u64 *)(r1 +0) = r6")
+__xlated("11: r0 = r6")
+__xlated("12: r0 *= 2")
+__xlated("13: exit")
+SEC("struct_ops/test_epilogue")
+__naked int test_epilogue(void)
+{
+	asm volatile (
+	"r1 = *(u64 *)(r1 +0);"
+	"r6 = r1;"
+	"call %[bpf_kfunc_st_ops_inc10];"
+	"r1 = r6;"
+	"call subprog;"
+	"exit;"
+	:
+	: __imm(bpf_kfunc_st_ops_inc10)
+	: __clobber_all);
+}
+
+__success
+/* prologue */
+__xlated("0: r6 = *(u64 *)(r1 +0)")
+__xlated("1: r7 = *(u64 *)(r6 +0)")
+__xlated("2: r7 += 1000")
+__xlated("3: *(u64 *)(r6 +0) = r7")
+/* save __u64 *ctx to stack */
+__xlated("4: *(u64 *)(r10 -8) = r1")
+/* main prog */
+__xlated("5: r1 = *(u64 *)(r1 +0)")
+__xlated("6: r6 = r1")
+__xlated("7: call kernel-function")
+__xlated("8: r1 = r6")
+__xlated("9: call pc+")
+/* epilogue */
+__xlated("10: r1 = *(u64 *)(r10 -8)")
+__xlated("11: r1 = *(u64 *)(r1 +0)")
+__xlated("12: r6 = *(u64 *)(r1 +0)")
+__xlated("13: r6 += 10000")
+__xlated("14: *(u64 *)(r1 +0) = r6")
+__xlated("15: r0 = r6")
+__xlated("16: r0 *= 2")
+__xlated("17: exit")
+SEC("struct_ops/test_pro_epilogue")
+__naked int test_pro_epilogue(void)
+{
+	asm volatile (
+	"r1 = *(u64 *)(r1 +0);"
+	"r6 = r1;"
+	"call %[bpf_kfunc_st_ops_inc10];"
+	"r1 = r6;"
+	"call subprog;"
+	"exit;"
+	:
+	: __imm(bpf_kfunc_st_ops_inc10)
+	: __clobber_all);
+}
+
+SEC("syscall")
+__retval(1011) /* PROLOGUE_A [1000] + KFUNC_INC10 + SUBPROG_A [1] */
+int syscall_prologue(void *ctx)
+{
+	struct st_ops_args args = {};
+
+	return bpf_kfunc_st_ops_test_prologue(&args);
+}
+
+SEC("syscall")
+__retval(20022) /* (KFUNC_INC10 + SUBPROG_A [1] + EPILOGUE_A [10000]) * 2 */
+int syscall_epilogue(void *ctx)
+{
+	struct st_ops_args args = {};
+
+	return bpf_kfunc_st_ops_test_epilogue(&args);
+}
+
+SEC("syscall")
+__retval(22022) /* (PROLOGUE_A [1000] + KFUNC_INC10 + SUBPROG_A [1] + EPILOGUE_A [10000]) * 2 */
+int syscall_pro_epilogue(void *ctx)
+{
+	struct st_ops_args args = {};
+
+	return bpf_kfunc_st_ops_test_pro_epilogue(&args);
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_st_ops pro_epilogue = {
+	.test_prologue = (void *)test_prologue,
+	.test_epilogue = (void *)test_epilogue,
+	.test_pro_epilogue = (void *)test_pro_epilogue,
+};
diff --git a/tools/testing/selftests/bpf/progs/pro_epilogue_goto_start.c b/tools/testing/selftests/bpf/progs/pro_epilogue_goto_start.c
new file mode 100644
index 000000000000..3529e53be355
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/pro_epilogue_goto_start.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../bpf_testmod/bpf_testmod.h"
+#include "../bpf_testmod/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+__success
+/* prologue */
+__xlated("0: r6 = *(u64 *)(r1 +0)")
+__xlated("1: r7 = *(u64 *)(r6 +0)")
+__xlated("2: r7 += 1000")
+__xlated("3: *(u64 *)(r6 +0) = r7")
+/* main prog */
+__xlated("4: if r1 == 0x0 goto pc+5")
+__xlated("5: if r1 == 0x1 goto pc+2")
+__xlated("6: r1 = 1")
+__xlated("7: goto pc-3")
+__xlated("8: r1 = 0")
+__xlated("9: goto pc-6")
+__xlated("10: r0 = 0")
+__xlated("11: exit")
+SEC("struct_ops/test_prologue_goto_start")
+__naked int test_prologue_goto_start(void)
+{
+	asm volatile (
+	"if r1 == 0 goto +5;"
+	"if r1 == 1 goto +2;"
+	"r1 = 1;"
+	"goto -3;"
+	"r1 = 0;"
+	"goto -6;"
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+__success
+/* save __u64 *ctx to stack */
+__xlated("0: *(u64 *)(r10 -8) = r1")
+/* main prog */
+__xlated("1: if r1 == 0x0 goto pc+5")
+__xlated("2: if r1 == 0x1 goto pc+2")
+__xlated("3: r1 = 1")
+__xlated("4: goto pc-3")
+__xlated("5: r1 = 0")
+__xlated("6: goto pc-6")
+__xlated("7: r0 = 0")
+/* epilogue */
+__xlated("8: r1 = *(u64 *)(r10 -8)")
+__xlated("9: r1 = *(u64 *)(r1 +0)")
+__xlated("10: r6 = *(u64 *)(r1 +0)")
+__xlated("11: r6 += 10000")
+__xlated("12: *(u64 *)(r1 +0) = r6")
+__xlated("13: r0 = r6")
+__xlated("14: r0 *= 2")
+__xlated("15: exit")
+SEC("struct_ops/test_epilogue_goto_start")
+__naked int test_epilogue_goto_start(void)
+{
+	asm volatile (
+	"if r1 == 0 goto +5;"
+	"if r1 == 1 goto +2;"
+	"r1 = 1;"
+	"goto -3;"
+	"r1 = 0;"
+	"goto -6;"
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+__success
+/* prologue */
+__xlated("0: r6 = *(u64 *)(r1 +0)")
+__xlated("1: r7 = *(u64 *)(r6 +0)")
+__xlated("2: r7 += 1000")
+__xlated("3: *(u64 *)(r6 +0) = r7")
+/* save __u64 *ctx to stack */
+__xlated("4: *(u64 *)(r10 -8) = r1")
+/* main prog */
+__xlated("5: if r1 == 0x0 goto pc+5")
+__xlated("6: if r1 == 0x1 goto pc+2")
+__xlated("7: r1 = 1")
+__xlated("8: goto pc-3")
+__xlated("9: r1 = 0")
+__xlated("10: goto pc-6")
+__xlated("11: r0 = 0")
+/* epilogue */
+__xlated("12: r1 = *(u64 *)(r10 -8)")
+__xlated("13: r1 = *(u64 *)(r1 +0)")
+__xlated("14: r6 = *(u64 *)(r1 +0)")
+__xlated("15: r6 += 10000")
+__xlated("16: *(u64 *)(r1 +0) = r6")
+__xlated("17: r0 = r6")
+__xlated("18: r0 *= 2")
+__xlated("19: exit")
+SEC("struct_ops/test_pro_epilogue_goto_start")
+__naked int test_pro_epilogue_goto_start(void)
+{
+	asm volatile (
+	"if r1 == 0 goto +5;"
+	"if r1 == 1 goto +2;"
+	"r1 = 1;"
+	"goto -3;"
+	"r1 = 0;"
+	"goto -6;"
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_st_ops epilogue_goto_start = {
+	.test_prologue = (void *)test_prologue_goto_start,
+	.test_epilogue = (void *)test_epilogue_goto_start,
+	.test_pro_epilogue = (void *)test_pro_epilogue_goto_start,
+};
+
+SEC("syscall")
+__retval(0)
+int syscall_prologue_goto_start(void *ctx)
+{
+	struct st_ops_args args = {};
+
+	return bpf_kfunc_st_ops_test_prologue(&args);
+}
+
+SEC("syscall")
+__retval(20000) /* (EPILOGUE_A [10000]) * 2 */
+int syscall_epilogue_goto_start(void *ctx)
+{
+	struct st_ops_args args = {};
+
+	return bpf_kfunc_st_ops_test_epilogue(&args);
+}
+
+SEC("syscall")
+__retval(22000) /* (PROLOGUE_A [1000] + EPILOGUE_A [10000]) * 2 */
+int syscall_pro_epilogue_goto_start(void *ctx)
+{
+	struct st_ops_args args = {};
+
+	return bpf_kfunc_st_ops_test_pro_epilogue(&args);
+}
diff --git a/tools/testing/selftests/bpf/progs/rbtree_fail.c b/tools/testing/selftests/bpf/progs/rbtree_fail.c
index b722a1e1ddef..dbd5eee8e25e 100644
--- a/tools/testing/selftests/bpf/progs/rbtree_fail.c
+++ b/tools/testing/selftests/bpf/progs/rbtree_fail.c
@@ -105,7 +105,7 @@ long rbtree_api_remove_unadded_node(void *ctx)
 }
 
 SEC("?tc")
-__failure __regex("Unreleased reference id=3 alloc_insn=[0-9]+")
+__failure __msg("Unreleased reference id=3 alloc_insn={{[0-9]+}}")
 long rbtree_api_remove_no_drop(void *ctx)
 {
 	struct bpf_rb_node *res;
diff --git a/tools/testing/selftests/bpf/progs/read_vsyscall.c b/tools/testing/selftests/bpf/progs/read_vsyscall.c
index 986f96687ae1..39ebef430059 100644
--- a/tools/testing/selftests/bpf/progs/read_vsyscall.c
+++ b/tools/testing/selftests/bpf/progs/read_vsyscall.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (C) 2024. Huawei Technologies Co., Ltd */
+#include "vmlinux.h"
 #include <linux/types.h>
 #include <bpf/bpf_helpers.h>
 
@@ -7,10 +8,15 @@
 
 int target_pid = 0;
 void *user_ptr = 0;
-int read_ret[8];
+int read_ret[9];
 
 char _license[] SEC("license") = "GPL";
 
+/*
+ * This is the only kfunc, the others are helpers
+ */
+int bpf_copy_from_user_str(void *dst, u32, const void *, u64) __weak __ksym;
+
 SEC("fentry/" SYS_PREFIX "sys_nanosleep")
 int do_probe_read(void *ctx)
 {
@@ -40,6 +46,7 @@ int do_copy_from_user(void *ctx)
 	read_ret[6] = bpf_copy_from_user(buf, sizeof(buf), user_ptr);
 	read_ret[7] = bpf_copy_from_user_task(buf, sizeof(buf), user_ptr,
 					      bpf_get_current_task_btf(), 0);
+	read_ret[8] = bpf_copy_from_user_str((char *)buf, sizeof(buf), user_ptr, 0);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
index f8d4b7cfcd68..836c8ab7b908 100644
--- a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
+++ b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
@@ -32,7 +32,7 @@ static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
 }
 
 SEC("?tc")
-__failure __regex("Unreleased reference id=4 alloc_insn=[0-9]+")
+__failure __msg("Unreleased reference id=4 alloc_insn={{[0-9]+}}")
 long rbtree_refcounted_node_ref_escapes(void *ctx)
 {
 	struct node_acquire *n, *m;
@@ -73,7 +73,7 @@ long refcount_acquire_maybe_null(void *ctx)
 }
 
 SEC("?tc")
-__failure __regex("Unreleased reference id=3 alloc_insn=[0-9]+")
+__failure __msg("Unreleased reference id=3 alloc_insn={{[0-9]+}}")
 long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx)
 {
 	struct node_acquire *n, *m;
diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h
index f74459eead26..a5c74d31a244 100644
--- a/tools/testing/selftests/bpf/progs/strobemeta.h
+++ b/tools/testing/selftests/bpf/progs/strobemeta.h
@@ -373,7 +373,7 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg,
 	len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, value->ptr);
 	/*
 	 * if bpf_probe_read_user_str returns error (<0), due to casting to
-	 * unsinged int, it will become big number, so next check is
+	 * unsigned int, it will become big number, so next check is
 	 * sufficient to check for errors AND prove to BPF verifier, that
 	 * bpf_probe_read_user_str won't return anything bigger than
 	 * STROBE_MAX_STR_LEN
@@ -557,7 +557,7 @@ static void *read_strobe_meta(struct task_struct *task,
 		return NULL;
 
 	payload_off = ctx.payload_off;
-	/* this should not really happen, here only to satisfy verifer */
+	/* this should not really happen, here only to satisfy verifier */
 	if (payload_off > sizeof(data->payload))
 		payload_off = sizeof(data->payload);
 #else
diff --git a/tools/testing/selftests/bpf/progs/syscall.c b/tools/testing/selftests/bpf/progs/syscall.c
index 3d3cafdebe72..0f4dfb770c32 100644
--- a/tools/testing/selftests/bpf/progs/syscall.c
+++ b/tools/testing/selftests/bpf/progs/syscall.c
@@ -8,6 +8,7 @@
 #include <linux/btf.h>
 #include <string.h>
 #include <errno.h>
+#include "bpf_misc.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -119,7 +120,7 @@ int load_prog(struct args *ctx)
 	static __u64 value = 34;
 	static union bpf_attr prog_load_attr = {
 		.prog_type = BPF_PROG_TYPE_XDP,
-		.insn_cnt = sizeof(insns) / sizeof(insns[0]),
+		.insn_cnt = ARRAY_SIZE(insns),
 	};
 	int ret;
 
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy1.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy1.c
new file mode 100644
index 000000000000..327ca395e860
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy1.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_legacy.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+int count = 0;
+
+static __noinline
+int subprog_tail(struct __sk_buff *skb)
+{
+	bpf_tail_call_static(skb, &jmp_table, 0);
+	return 0;
+}
+
+SEC("tc")
+int entry(struct __sk_buff *skb)
+{
+	int ret = 1;
+
+	count++;
+	subprog_tail(skb);
+	subprog_tail(skb);
+
+	return ret;
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy2.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy2.c
new file mode 100644
index 000000000000..72fd0d577506
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy2.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+int classifier_0(struct __sk_buff *skb);
+int classifier_1(struct __sk_buff *skb);
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 2);
+	__uint(key_size, sizeof(__u32));
+	__array(values, void (void));
+} jmp_table SEC(".maps") = {
+	.values = {
+		[0] = (void *) &classifier_0,
+		[1] = (void *) &classifier_1,
+	},
+};
+
+int count0 = 0;
+int count1 = 0;
+
+static __noinline
+int subprog_tail0(struct __sk_buff *skb)
+{
+	bpf_tail_call_static(skb, &jmp_table, 0);
+	return 0;
+}
+
+__auxiliary
+SEC("tc")
+int classifier_0(struct __sk_buff *skb)
+{
+	count0++;
+	subprog_tail0(skb);
+	return 0;
+}
+
+static __noinline
+int subprog_tail1(struct __sk_buff *skb)
+{
+	bpf_tail_call_static(skb, &jmp_table, 1);
+	return 0;
+}
+
+__auxiliary
+SEC("tc")
+int classifier_1(struct __sk_buff *skb)
+{
+	count1++;
+	subprog_tail1(skb);
+	return 0;
+}
+
+__success
+__retval(33)
+SEC("tc")
+int tailcall_bpf2bpf_hierarchy_2(struct __sk_buff *skb)
+{
+	int ret = 0;
+
+	subprog_tail0(skb);
+	subprog_tail1(skb);
+
+	__sink(ret);
+	return (count1 << 16) | count0;
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy3.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy3.c
new file mode 100644
index 000000000000..a7fb91cb05b7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy3.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+int classifier_0(struct __sk_buff *skb);
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__array(values, void (void));
+} jmp_table0 SEC(".maps") = {
+	.values = {
+		[0] = (void *) &classifier_0,
+	},
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__array(values, void (void));
+} jmp_table1 SEC(".maps") = {
+	.values = {
+		[0] = (void *) &classifier_0,
+	},
+};
+
+int count = 0;
+
+static __noinline
+int subprog_tail(struct __sk_buff *skb, void *jmp_table)
+{
+	bpf_tail_call_static(skb, jmp_table, 0);
+	return 0;
+}
+
+__auxiliary
+SEC("tc")
+int classifier_0(struct __sk_buff *skb)
+{
+	count++;
+	subprog_tail(skb, &jmp_table0);
+	subprog_tail(skb, &jmp_table1);
+	return count;
+}
+
+__success
+__retval(33)
+SEC("tc")
+int tailcall_bpf2bpf_hierarchy_3(struct __sk_buff *skb)
+{
+	int ret = 0;
+
+	bpf_tail_call_static(skb, &jmp_table0, 0);
+
+	__sink(ret);
+	return ret;
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy_fentry.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy_fentry.c
new file mode 100644
index 000000000000..c87f9ca982d3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy_fentry.c
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Leon Hwang */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+int count = 0;
+
+static __noinline
+int subprog_tail(void *ctx)
+{
+	bpf_tail_call_static(ctx, &jmp_table, 0);
+	return 0;
+}
+
+SEC("fentry/dummy")
+int BPF_PROG(fentry, struct sk_buff *skb)
+{
+	count++;
+	subprog_tail(ctx);
+	subprog_tail(ctx);
+
+	return 0;
+}
+
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tailcall_freplace.c b/tools/testing/selftests/bpf/progs/tailcall_freplace.c
new file mode 100644
index 000000000000..6713b809df44
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_freplace.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+int count = 0;
+
+SEC("freplace")
+int entry_freplace(struct __sk_buff *skb)
+{
+	count++;
+	bpf_tail_call_static(skb, &jmp_table, 0);
+	return count;
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_success.c b/tools/testing/selftests/bpf/progs/task_kfunc_success.c
index 70df695312dc..a55149015063 100644
--- a/tools/testing/selftests/bpf/progs/task_kfunc_success.c
+++ b/tools/testing/selftests/bpf/progs/task_kfunc_success.c
@@ -5,6 +5,7 @@
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_helpers.h>
 
+#include "../bpf_experimental.h"
 #include "task_kfunc_common.h"
 
 char _license[] SEC("license") = "GPL";
@@ -142,8 +143,9 @@ int BPF_PROG(test_task_acquire_leave_in_map, struct task_struct *task, u64 clone
 SEC("tp_btf/task_newtask")
 int BPF_PROG(test_task_xchg_release, struct task_struct *task, u64 clone_flags)
 {
-	struct task_struct *kptr;
-	struct __tasks_kfunc_map_value *v;
+	struct task_struct *kptr, *acquired;
+	struct __tasks_kfunc_map_value *v, *local;
+	int refcnt, refcnt_after_drop;
 	long status;
 
 	if (!is_test_kfunc_task())
@@ -167,6 +169,56 @@ int BPF_PROG(test_task_xchg_release, struct task_struct *task, u64 clone_flags)
 		return 0;
 	}
 
+	local = bpf_obj_new(typeof(*local));
+	if (!local) {
+		err = 4;
+		bpf_task_release(kptr);
+		return 0;
+	}
+
+	kptr = bpf_kptr_xchg(&local->task, kptr);
+	if (kptr) {
+		err = 5;
+		bpf_obj_drop(local);
+		bpf_task_release(kptr);
+		return 0;
+	}
+
+	kptr = bpf_kptr_xchg(&local->task, NULL);
+	if (!kptr) {
+		err = 6;
+		bpf_obj_drop(local);
+		return 0;
+	}
+
+	/* Stash a copy into local kptr and check if it is released recursively */
+	acquired = bpf_task_acquire(kptr);
+	if (!acquired) {
+		err = 7;
+		bpf_obj_drop(local);
+		bpf_task_release(kptr);
+		return 0;
+	}
+	bpf_probe_read_kernel(&refcnt, sizeof(refcnt), &acquired->rcu_users);
+
+	acquired = bpf_kptr_xchg(&local->task, acquired);
+	if (acquired) {
+		err = 8;
+		bpf_obj_drop(local);
+		bpf_task_release(kptr);
+		bpf_task_release(acquired);
+		return 0;
+	}
+
+	bpf_obj_drop(local);
+
+	bpf_probe_read_kernel(&refcnt_after_drop, sizeof(refcnt_after_drop), &kptr->rcu_users);
+	if (refcnt != refcnt_after_drop + 1) {
+		err = 9;
+		bpf_task_release(kptr);
+		return 0;
+	}
+
 	bpf_task_release(kptr);
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c
new file mode 100644
index 000000000000..8a0632c37839
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+__noinline
+int subprog(struct __sk_buff *skb)
+{
+	int ret = 1;
+
+	__sink(ret);
+	return ret;
+}
+
+SEC("tc")
+int entry_tc(struct __sk_buff *skb)
+{
+	return subprog(skb);
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tc_dummy.c b/tools/testing/selftests/bpf/progs/tc_dummy.c
new file mode 100644
index 000000000000..69a3d0dc8787
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tc_dummy.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_legacy.h"
+
+SEC("tc")
+int entry(struct __sk_buff *skb)
+{
+	return 1;
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c
index 68466a6ad18c..fb79e6cab932 100644
--- a/tools/testing/selftests/bpf/progs/test_attach_probe.c
+++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c
@@ -5,8 +5,10 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_core_read.h>
+#include <errno.h>
 #include "bpf_misc.h"
 
+u32 dynamic_sz = 1;
 int kprobe2_res = 0;
 int kretprobe2_res = 0;
 int uprobe_byname_res = 0;
@@ -14,11 +16,15 @@ int uretprobe_byname_res = 0;
 int uprobe_byname2_res = 0;
 int uretprobe_byname2_res = 0;
 int uprobe_byname3_sleepable_res = 0;
+int uprobe_byname3_str_sleepable_res = 0;
 int uprobe_byname3_res = 0;
 int uretprobe_byname3_sleepable_res = 0;
+int uretprobe_byname3_str_sleepable_res = 0;
 int uretprobe_byname3_res = 0;
 void *user_ptr = 0;
 
+int bpf_copy_from_user_str(void *dst, u32, const void *, u64) __weak __ksym;
+
 SEC("ksyscall/nanosleep")
 int BPF_KSYSCALL(handle_kprobe_auto, struct __kernel_timespec *req, struct __kernel_timespec *rem)
 {
@@ -87,11 +93,61 @@ static __always_inline bool verify_sleepable_user_copy(void)
 	return bpf_strncmp(data, sizeof(data), "test_data") == 0;
 }
 
+static __always_inline bool verify_sleepable_user_copy_str(void)
+{
+	int ret;
+	char data_long[20];
+	char data_long_pad[20];
+	char data_long_err[20];
+	char data_short[4];
+	char data_short_pad[4];
+
+	ret = bpf_copy_from_user_str(data_short, sizeof(data_short), user_ptr, 0);
+
+	if (bpf_strncmp(data_short, 4, "tes\0") != 0 || ret != 4)
+		return false;
+
+	ret = bpf_copy_from_user_str(data_short_pad, sizeof(data_short_pad), user_ptr, BPF_F_PAD_ZEROS);
+
+	if (bpf_strncmp(data_short, 4, "tes\0") != 0 || ret != 4)
+		return false;
+
+	/* Make sure this passes the verifier */
+	ret = bpf_copy_from_user_str(data_long, dynamic_sz & sizeof(data_long), user_ptr, 0);
+
+	if (ret != 0)
+		return false;
+
+	ret = bpf_copy_from_user_str(data_long, sizeof(data_long), user_ptr, 0);
+
+	if (bpf_strncmp(data_long, 10, "test_data\0") != 0 || ret != 10)
+		return false;
+
+	ret = bpf_copy_from_user_str(data_long_pad, sizeof(data_long_pad), user_ptr, BPF_F_PAD_ZEROS);
+
+	if (bpf_strncmp(data_long_pad, 10, "test_data\0") != 0 || ret != 10 || data_long_pad[19] != '\0')
+		return false;
+
+	ret = bpf_copy_from_user_str(data_long_err, sizeof(data_long_err), (void *)data_long, BPF_F_PAD_ZEROS);
+
+	if (ret > 0 || data_long_err[19] != '\0')
+		return false;
+
+	ret = bpf_copy_from_user_str(data_long, sizeof(data_long), user_ptr, 2);
+
+	if (ret != -EINVAL)
+		return false;
+
+	return true;
+}
+
 SEC("uprobe.s//proc/self/exe:trigger_func3")
 int handle_uprobe_byname3_sleepable(struct pt_regs *ctx)
 {
 	if (verify_sleepable_user_copy())
 		uprobe_byname3_sleepable_res = 9;
+	if (verify_sleepable_user_copy_str())
+		uprobe_byname3_str_sleepable_res = 10;
 	return 0;
 }
 
@@ -102,7 +158,7 @@ int handle_uprobe_byname3_sleepable(struct pt_regs *ctx)
 SEC("uprobe//proc/self/exe:trigger_func3")
 int handle_uprobe_byname3(struct pt_regs *ctx)
 {
-	uprobe_byname3_res = 10;
+	uprobe_byname3_res = 11;
 	return 0;
 }
 
@@ -110,14 +166,16 @@ SEC("uretprobe.s//proc/self/exe:trigger_func3")
 int handle_uretprobe_byname3_sleepable(struct pt_regs *ctx)
 {
 	if (verify_sleepable_user_copy())
-		uretprobe_byname3_sleepable_res = 11;
+		uretprobe_byname3_sleepable_res = 12;
+	if (verify_sleepable_user_copy_str())
+		uretprobe_byname3_str_sleepable_res = 13;
 	return 0;
 }
 
 SEC("uretprobe//proc/self/exe:trigger_func3")
 int handle_uretprobe_byname3(struct pt_regs *ctx)
 {
-	uretprobe_byname3_res = 12;
+	uretprobe_byname3_res = 14;
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_build_id.c b/tools/testing/selftests/bpf/progs/test_build_id.c
new file mode 100644
index 000000000000..32ce59f9aa27
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_build_id.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+struct bpf_stack_build_id stack_sleepable[128];
+int res_sleepable;
+
+struct bpf_stack_build_id stack_nofault[128];
+int res_nofault;
+
+SEC("uprobe.multi/./uprobe_multi:uprobe")
+int uprobe_nofault(struct pt_regs *ctx)
+{
+	res_nofault = bpf_get_stack(ctx, stack_nofault, sizeof(stack_nofault),
+				    BPF_F_USER_STACK | BPF_F_USER_BUILD_ID);
+
+	return 0;
+}
+
+SEC("uprobe.multi.s/./uprobe_multi:uprobe")
+int uprobe_sleepable(struct pt_regs *ctx)
+{
+	res_sleepable = bpf_get_stack(ctx, stack_sleepable, sizeof(stack_sleepable),
+				      BPF_F_USER_STACK | BPF_F_USER_BUILD_ID);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
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 da54c09e9a15..464515b824b9 100644
--- a/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c
@@ -503,7 +503,7 @@ static ret_t get_next_hop(struct bpf_dynptr *dynptr, __u64 *offset, encap_header
  *
  *    fill_tuple(&t, foo, sizeof(struct iphdr), 123, 321)
  *
- * clang will substitue a costant for sizeof, which allows the verifier
+ * clang will substitute a constant for sizeof, which allows the verifier
  * to track it's value. Based on this, it can figure out the constant
  * return value, and calling code works while still being "generic" to
  * IPv4 and IPv6.
diff --git a/tools/testing/selftests/bpf/progs/test_core_read_macros.c b/tools/testing/selftests/bpf/progs/test_core_read_macros.c
index fd54caa17319..873d85a4739b 100644
--- a/tools/testing/selftests/bpf/progs/test_core_read_macros.c
+++ b/tools/testing/selftests/bpf/progs/test_core_read_macros.c
@@ -36,7 +36,7 @@ int handler(void *ctx)
 		return 0;
 
 	/* next pointers for kernel address space have to be initialized from
-	 * BPF side, user-space mmaped addresses are stil user-space addresses
+	 * BPF side, user-space mmaped addresses are still user-space addresses
 	 */
 	k_probe_in.next = &k_probe_in;
 	__builtin_preserve_access_index(({k_core_in.next = &k_core_in;}));
diff --git a/tools/testing/selftests/bpf/progs/test_get_xattr.c b/tools/testing/selftests/bpf/progs/test_get_xattr.c
index 7eb2a4e5a3e5..66e737720f7c 100644
--- a/tools/testing/selftests/bpf/progs/test_get_xattr.c
+++ b/tools/testing/selftests/bpf/progs/test_get_xattr.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
 
 #include "vmlinux.h"
+#include <errno.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include "bpf_kfuncs.h"
@@ -9,10 +10,12 @@
 char _license[] SEC("license") = "GPL";
 
 __u32 monitored_pid;
-__u32 found_xattr;
+__u32 found_xattr_from_file;
+__u32 found_xattr_from_dentry;
 
 static const char expected_value[] = "hello";
-char value[32];
+char value1[32];
+char value2[32];
 
 SEC("lsm.s/file_open")
 int BPF_PROG(test_file_open, struct file *f)
@@ -25,13 +28,37 @@ int BPF_PROG(test_file_open, struct file *f)
 	if (pid != monitored_pid)
 		return 0;
 
-	bpf_dynptr_from_mem(value, sizeof(value), 0, &value_ptr);
+	bpf_dynptr_from_mem(value1, sizeof(value1), 0, &value_ptr);
 
 	ret = bpf_get_file_xattr(f, "user.kfuncs", &value_ptr);
 	if (ret != sizeof(expected_value))
 		return 0;
-	if (bpf_strncmp(value, ret, expected_value))
+	if (bpf_strncmp(value1, ret, expected_value))
 		return 0;
-	found_xattr = 1;
+	found_xattr_from_file = 1;
 	return 0;
 }
+
+SEC("lsm.s/inode_getxattr")
+int BPF_PROG(test_inode_getxattr, struct dentry *dentry, char *name)
+{
+	struct bpf_dynptr value_ptr;
+	__u32 pid;
+	int ret;
+
+	pid = bpf_get_current_pid_tgid() >> 32;
+	if (pid != monitored_pid)
+		return 0;
+
+	bpf_dynptr_from_mem(value2, sizeof(value2), 0, &value_ptr);
+
+	ret = bpf_get_dentry_xattr(dentry, "user.kfuncs", &value_ptr);
+	if (ret != sizeof(expected_value))
+		return 0;
+	if (bpf_strncmp(value2, ret, expected_value))
+		return 0;
+	found_xattr_from_dentry = 1;
+
+	/* return non-zero to fail getxattr from user space */
+	return -EINVAL;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func15.c b/tools/testing/selftests/bpf/progs/test_global_func15.c
index b4e089d6981d..201cc000b3f4 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func15.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func15.c
@@ -44,7 +44,7 @@ __naked int global_func15_tricky_pruning(void)
 		 * case we have a valid 1 stored in R0 register, but in
 		 * a branch case we assign some random value to R0.  So if
 		 * there is something wrong with precision tracking for R0 at
-		 * program exit, we might erronenously prune branch case,
+		 * program exit, we might erroneously prune branch case,
 		 * because R0 in fallthrough case is imprecise (and thus any
 		 * value is valid from POV of verifier is_state_equal() logic)
 		 */
diff --git a/tools/testing/selftests/bpf/progs/test_global_map_resize.c b/tools/testing/selftests/bpf/progs/test_global_map_resize.c
index 1fbb73d3e5d5..a3f220ba7025 100644
--- a/tools/testing/selftests/bpf/progs/test_global_map_resize.c
+++ b/tools/testing/selftests/bpf/progs/test_global_map_resize.c
@@ -3,6 +3,7 @@
 
 #include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
@@ -15,7 +16,7 @@ const volatile size_t data_array_len;
 int sum = 0;
 int array[1];
 
-/* custom data secton */
+/* custom data section */
 int my_array[1] SEC(".data.custom");
 
 /* custom data section which should NOT be resizable,
@@ -60,3 +61,18 @@ int data_array_sum(void *ctx)
 
 	return 0;
 }
+
+SEC("struct_ops/test_1")
+int BPF_PROG(test_1)
+{
+	return 0;
+}
+
+struct bpf_testmod_ops {
+	int (*test_1)(void);
+};
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops st_ops_resize = {
+	.test_1 = (void *)test_1
+};
diff --git a/tools/testing/selftests/bpf/progs/test_libbpf_get_fd_by_id_opts.c b/tools/testing/selftests/bpf/progs/test_libbpf_get_fd_by_id_opts.c
index f5ac5f3e8919..568816307f71 100644
--- a/tools/testing/selftests/bpf/progs/test_libbpf_get_fd_by_id_opts.c
+++ b/tools/testing/selftests/bpf/progs/test_libbpf_get_fd_by_id_opts.c
@@ -31,6 +31,7 @@ int BPF_PROG(check_access, struct bpf_map *map, fmode_t fmode)
 
 	if (fmode & FMODE_WRITE)
 		return -EACCES;
+	barrier();
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c
index fc8e8a34a3db..7035fb4d4165 100644
--- a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c
+++ b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c
@@ -4,6 +4,7 @@
 #include <linux/ptrace.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 const struct {
 	unsigned a[4];
@@ -64,7 +65,7 @@ int full_loop(struct pt_regs *ctx)
 {
 	/* prevent compiler to optimize everything out */
 	unsigned * volatile p = (void *)&rdonly_values.a;
-	int i = sizeof(rdonly_values.a) / sizeof(rdonly_values.a[0]);
+	int i = ARRAY_SIZE(rdonly_values.a);
 	unsigned iters = 0, sum = 0;
 
 	/* validate verifier can allow full loop as well */
diff --git a/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c b/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c
index 2f0eb1334d65..8ef6b39335b6 100644
--- a/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c
+++ b/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c
@@ -6,6 +6,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include "bpf_kfuncs.h"
+#include "err.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -79,5 +80,8 @@ int BPF_PROG(test_file_open, struct file *f)
 	ret = bpf_verify_pkcs7_signature(&digest_ptr, &sig_ptr, trusted_keyring);
 
 	bpf_key_put(trusted_keyring);
+
+	set_if_not_errno_or_zero(ret, -EFAULT);
+
 	return ret;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c
deleted file mode 100644
index 37aacc66cd68..000000000000
--- a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c
+++ /dev/null
@@ -1,45 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (c) 2018 Facebook
-
-#include <linux/bpf.h>
-#include <linux/pkt_cls.h>
-
-#include <string.h>
-
-#include <bpf/bpf_helpers.h>
-
-#define NUM_CGROUP_LEVELS	4
-
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__type(key, __u32);
-	__type(value, __u64);
-	__uint(max_entries, NUM_CGROUP_LEVELS);
-} cgroup_ids SEC(".maps");
-
-static __always_inline void log_nth_level(struct __sk_buff *skb, __u32 level)
-{
-	__u64 id;
-
-	/* [1] &level passed to external function that may change it, it's
-	 *     incompatible with loop unroll.
-	 */
-	id = bpf_skb_ancestor_cgroup_id(skb, level);
-	bpf_map_update_elem(&cgroup_ids, &level, &id, 0);
-}
-
-SEC("cgroup_id_logger")
-int log_cgroup_id(struct __sk_buff *skb)
-{
-	/* Loop unroll can't be used here due to [1]. Unrolling manually.
-	 * Number of calls should be in sync with NUM_CGROUP_LEVELS.
-	 */
-	log_nth_level(skb, 0);
-	log_nth_level(skb, 1);
-	log_nth_level(skb, 2);
-	log_nth_level(skb, 3);
-
-	return TC_ACT_OK;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index 3f5abcf3ff13..32127f1cd687 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -26,6 +26,18 @@
  */
 #define ASSIGNED_ADDR_VETH1 0xac1001c8
 
+struct bpf_fou_encap___local {
+	__be16 sport;
+	__be16 dport;
+} __attribute__((preserve_access_index));
+
+enum bpf_fou_encap_type___local {
+	FOU_BPF_ENCAP_FOU___local,
+	FOU_BPF_ENCAP_GUE___local,
+};
+
+struct bpf_fou_encap;
+
 int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx,
 			  struct bpf_fou_encap *encap, int type) __ksym;
 int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx,
@@ -745,7 +757,7 @@ SEC("tc")
 int ipip_gue_set_tunnel(struct __sk_buff *skb)
 {
 	struct bpf_tunnel_key key = {};
-	struct bpf_fou_encap encap = {};
+	struct bpf_fou_encap___local encap = {};
 	void *data = (void *)(long)skb->data;
 	struct iphdr *iph = data;
 	void *data_end = (void *)(long)skb->data_end;
@@ -769,7 +781,9 @@ int ipip_gue_set_tunnel(struct __sk_buff *skb)
 	encap.sport = 0;
 	encap.dport = bpf_htons(5555);
 
-	ret = bpf_skb_set_fou_encap(skb, &encap, FOU_BPF_ENCAP_GUE);
+	ret = bpf_skb_set_fou_encap(skb, (struct bpf_fou_encap *)&encap,
+				    bpf_core_enum_value(enum bpf_fou_encap_type___local,
+							FOU_BPF_ENCAP_GUE___local));
 	if (ret < 0) {
 		log_err(ret);
 		return TC_ACT_SHOT;
@@ -782,7 +796,7 @@ SEC("tc")
 int ipip_fou_set_tunnel(struct __sk_buff *skb)
 {
 	struct bpf_tunnel_key key = {};
-	struct bpf_fou_encap encap = {};
+	struct bpf_fou_encap___local encap = {};
 	void *data = (void *)(long)skb->data;
 	struct iphdr *iph = data;
 	void *data_end = (void *)(long)skb->data_end;
@@ -806,7 +820,8 @@ int ipip_fou_set_tunnel(struct __sk_buff *skb)
 	encap.sport = 0;
 	encap.dport = bpf_htons(5555);
 
-	ret = bpf_skb_set_fou_encap(skb, &encap, FOU_BPF_ENCAP_FOU);
+	ret = bpf_skb_set_fou_encap(skb, (struct bpf_fou_encap *)&encap,
+				    FOU_BPF_ENCAP_FOU___local);
 	if (ret < 0) {
 		log_err(ret);
 		return TC_ACT_SHOT;
@@ -820,7 +835,7 @@ int ipip_encap_get_tunnel(struct __sk_buff *skb)
 {
 	int ret;
 	struct bpf_tunnel_key key = {};
-	struct bpf_fou_encap encap = {};
+	struct bpf_fou_encap___local encap = {};
 
 	ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
 	if (ret < 0) {
@@ -828,7 +843,7 @@ int ipip_encap_get_tunnel(struct __sk_buff *skb)
 		return TC_ACT_SHOT;
 	}
 
-	ret = bpf_skb_get_fou_encap(skb, &encap);
+	ret = bpf_skb_get_fou_encap(skb, (struct bpf_fou_encap *)&encap);
 	if (ret < 0) {
 		log_err(ret);
 		return TC_ACT_SHOT;
diff --git a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
index f42e9f3831a1..12034a73ee2d 100644
--- a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
+++ b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
@@ -11,6 +11,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include "bpf_kfuncs.h"
+#include "err.h"
 
 #define MAX_DATA_SIZE (1024 * 1024)
 #define MAX_SIG_SIZE 1024
@@ -55,12 +56,12 @@ int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size)
 
 	ret = bpf_probe_read_kernel(&value, sizeof(value), &attr->value);
 	if (ret)
-		return ret;
+		goto out;
 
 	ret = bpf_copy_from_user(data_val, sizeof(struct data),
 				 (void *)(unsigned long)value);
 	if (ret)
-		return ret;
+		goto out;
 
 	if (data_val->data_len > sizeof(data_val->data))
 		return -EINVAL;
@@ -84,5 +85,8 @@ int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size)
 
 	bpf_key_put(trusted_keyring);
 
+out:
+	set_if_not_errno_or_zero(ret, -EFAULT);
+
 	return ret;
 }
diff --git a/tools/testing/selftests/bpf/progs/token_lsm.c b/tools/testing/selftests/bpf/progs/token_lsm.c
index e4d59b6ba743..a6002d073b1b 100644
--- a/tools/testing/selftests/bpf/progs/token_lsm.c
+++ b/tools/testing/selftests/bpf/progs/token_lsm.c
@@ -8,8 +8,8 @@
 char _license[] SEC("license") = "GPL";
 
 int my_pid;
-bool reject_capable;
-bool reject_cmd;
+int reject_capable;
+int reject_cmd;
 
 SEC("lsm/bpf_token_capable")
 int BPF_PROG(token_capable, struct bpf_token *token, int cap)
diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c
index 2619ed193c65..044a6d78923e 100644
--- a/tools/testing/selftests/bpf/progs/trigger_bench.c
+++ b/tools/testing/selftests/bpf/progs/trigger_bench.c
@@ -32,6 +32,13 @@ int bench_trigger_uprobe(void *ctx)
 	return 0;
 }
 
+SEC("?uprobe.multi")
+int bench_trigger_uprobe_multi(void *ctx)
+{
+	inc_counter();
+	return 0;
+}
+
 const volatile int batch_iters = 0;
 
 SEC("?raw_tp")
diff --git a/tools/testing/selftests/bpf/progs/unsupported_ops.c b/tools/testing/selftests/bpf/progs/unsupported_ops.c
new file mode 100644
index 000000000000..9180365a3568
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/unsupported_ops.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../bpf_testmod/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("struct_ops/unsupported_ops")
+__failure
+__msg("attach to unsupported member unsupported_ops of struct bpf_testmod_ops")
+int BPF_PROG(unsupported_ops)
+{
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod = {
+	.unsupported_ops = (void *)unsupported_ops,
+};
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_consumers.c b/tools/testing/selftests/bpf/progs/uprobe_multi_consumers.c
new file mode 100644
index 000000000000..7e0fdcbbd242
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi_consumers.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <stdbool.h>
+#include "bpf_kfuncs.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+__u64 uprobe_result[4];
+
+SEC("uprobe.multi")
+int uprobe_0(struct pt_regs *ctx)
+{
+	uprobe_result[0]++;
+	return 0;
+}
+
+SEC("uprobe.multi")
+int uprobe_1(struct pt_regs *ctx)
+{
+	uprobe_result[1]++;
+	return 0;
+}
+
+SEC("uprobe.multi")
+int uprobe_2(struct pt_regs *ctx)
+{
+	uprobe_result[2]++;
+	return 0;
+}
+
+SEC("uprobe.multi")
+int uprobe_3(struct pt_regs *ctx)
+{
+	uprobe_result[3]++;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_pid_filter.c b/tools/testing/selftests/bpf/progs/uprobe_multi_pid_filter.c
new file mode 100644
index 000000000000..67fcbad36661
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi_pid_filter.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u32 pids[3];
+__u32 test[3][2];
+
+static void update_pid(int idx)
+{
+	__u32 pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid == pids[idx])
+		test[idx][0]++;
+	else
+		test[idx][1]++;
+}
+
+SEC("uprobe.multi")
+int uprobe_multi_0(struct pt_regs *ctx)
+{
+	update_pid(0);
+	return 0;
+}
+
+SEC("uprobe.multi")
+int uprobe_multi_1(struct pt_regs *ctx)
+{
+	update_pid(1);
+	return 0;
+}
+
+SEC("uprobe.multi")
+int uprobe_multi_2(struct pt_regs *ctx)
+{
+	update_pid(2);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c
index 716113c2bce2..f4da4d508ddb 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c
@@ -87,7 +87,7 @@ int bits_memalloc(void)
 	int *bit;
 
 	__builtin_memset(&data, 0xf0, sizeof(data)); /* 4 * 16 */
-	bpf_for_each(bits, bit, &data[0], sizeof(data) / sizeof(u64))
+	bpf_for_each(bits, bit, &data[0], ARRAY_SIZE(data))
 		nr++;
 	return nr;
 }
diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
new file mode 100644
index 000000000000..9da97d2efcd9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
@@ -0,0 +1,900 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+#include <stdbool.h>
+#include "bpf_kfuncs.h"
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 8")
+__xlated("4: r5 = 5")
+__xlated("5: w0 = ")
+__xlated("6: r0 = &(void __percpu *)(r0)")
+__xlated("7: r0 = *(u32 *)(r0 +0)")
+__xlated("8: exit")
+__success
+__naked void simple(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"r2 = 2;"
+	"r3 = 3;"
+	"r4 = 4;"
+	"r5 = 5;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"*(u64 *)(r10 - 24) = r2;"
+	"*(u64 *)(r10 - 32) = r3;"
+	"*(u64 *)(r10 - 40) = r4;"
+	"*(u64 *)(r10 - 48) = r5;"
+	"call %[bpf_get_smp_processor_id];"
+	"r5 = *(u64 *)(r10 - 48);"
+	"r4 = *(u64 *)(r10 - 40);"
+	"r3 = *(u64 *)(r10 - 32);"
+	"r2 = *(u64 *)(r10 - 24);"
+	"r1 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+/* The logic for detecting and verifying bpf_fastcall pattern is the same for
+ * any arch, however x86 differs from arm64 or riscv64 in a way
+ * bpf_get_smp_processor_id is rewritten:
+ * - on x86 it is done by verifier
+ * - on arm64 and riscv64 it is done by jit
+ *
+ * Which leads to different xlated patterns for different archs:
+ * - on x86 the call is expanded as 3 instructions
+ * - on arm64 and riscv64 the call remains as is
+ *   (but spills/fills are still removed)
+ *
+ * It is really desirable to check instruction indexes in the xlated
+ * patterns, so add this canary test to check that function rewrite by
+ * jit is correctly processed by bpf_fastcall logic, keep the rest of the
+ * tests as x86.
+ */
+SEC("raw_tp")
+__arch_arm64
+__arch_riscv64
+__xlated("0: r1 = 1")
+__xlated("1: call bpf_get_smp_processor_id")
+__xlated("2: exit")
+__success
+__naked void canary_arm64_riscv64(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("3: exit")
+__success
+__naked void canary_zero_spills(void)
+{
+	asm volatile (
+	"call %[bpf_get_smp_processor_id];"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 16")
+__xlated("1: *(u64 *)(r10 -16) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r2 = *(u64 *)(r10 -16)")
+__success
+__naked void wrong_reg_in_pattern1(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r2 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -16) = r6")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r6 = *(u64 *)(r10 -16)")
+__success
+__naked void wrong_reg_in_pattern2(void)
+{
+	asm volatile (
+	"r6 = 1;"
+	"*(u64 *)(r10 - 16) = r6;"
+	"call %[bpf_get_smp_processor_id];"
+	"r6 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -16) = r0")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r0 = *(u64 *)(r10 -16)")
+__success
+__naked void wrong_reg_in_pattern3(void)
+{
+	asm volatile (
+	"r0 = 1;"
+	"*(u64 *)(r10 - 16) = r0;"
+	"call %[bpf_get_smp_processor_id];"
+	"r0 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("2: *(u64 *)(r2 -16) = r1")
+__xlated("...")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("6: r1 = *(u64 *)(r10 -16)")
+__success
+__naked void wrong_base_in_pattern(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"r2 = r10;"
+	"*(u64 *)(r2 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -16) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r2 = 1")
+__success
+__naked void wrong_insn_in_pattern(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r2 = 1;"
+	"r1 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("2: *(u64 *)(r10 -16) = r1")
+__xlated("...")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("6: r1 = *(u64 *)(r10 -8)")
+__success
+__naked void wrong_off_in_pattern1(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u32 *)(r10 -4) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r1 = *(u32 *)(r10 -4)")
+__success
+__naked void wrong_off_in_pattern2(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u32 *)(r10 - 4) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u32 *)(r10 - 4);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u32 *)(r10 -16) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r1 = *(u32 *)(r10 -16)")
+__success
+__naked void wrong_size_in_pattern(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u32 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u32 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("2: *(u32 *)(r10 -8) = r1")
+__xlated("...")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("6: r1 = *(u32 *)(r10 -8)")
+__success
+__naked void partial_pattern(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"r2 = 2;"
+	"*(u32 *)(r10 - 8) = r1;"
+	"*(u64 *)(r10 - 16) = r2;"
+	"call %[bpf_get_smp_processor_id];"
+	"r2 = *(u64 *)(r10 - 16);"
+	"r1 = *(u32 *)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("0: r1 = 1")
+__xlated("1: r2 = 2")
+/* not patched, spills for -8, -16 not removed */
+__xlated("2: *(u64 *)(r10 -8) = r1")
+__xlated("3: *(u64 *)(r10 -16) = r2")
+__xlated("...")
+__xlated("5: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("7: r2 = *(u64 *)(r10 -16)")
+__xlated("8: r1 = *(u64 *)(r10 -8)")
+/* patched, spills for -24, -32 removed */
+__xlated("...")
+__xlated("10: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("12: exit")
+__success
+__naked void min_stack_offset(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"r2 = 2;"
+	/* this call won't be patched */
+	"*(u64 *)(r10 - 8) = r1;"
+	"*(u64 *)(r10 - 16) = r2;"
+	"call %[bpf_get_smp_processor_id];"
+	"r2 = *(u64 *)(r10 - 16);"
+	"r1 = *(u64 *)(r10 - 8);"
+	/* this call would be patched */
+	"*(u64 *)(r10 - 24) = r1;"
+	"*(u64 *)(r10 - 32) = r2;"
+	"call %[bpf_get_smp_processor_id];"
+	"r2 = *(u64 *)(r10 - 32);"
+	"r1 = *(u64 *)(r10 - 24);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -8) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r1 = *(u64 *)(r10 -8)")
+__success
+__naked void bad_fixed_read(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"r1 = r10;"
+	"r1 += -8;"
+	"r1 = *(u64 *)(r1 - 0);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -8) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r1 = *(u64 *)(r10 -8)")
+__success
+__naked void bad_fixed_write(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"r1 = r10;"
+	"r1 += -8;"
+	"*(u64 *)(r1 - 0) = r1;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("6: *(u64 *)(r10 -16) = r1")
+__xlated("...")
+__xlated("8: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("10: r1 = *(u64 *)(r10 -16)")
+__success
+__naked void bad_varying_read(void)
+{
+	asm volatile (
+	"r6 = *(u64 *)(r1 + 0);" /* random scalar value */
+	"r6 &= 0x7;"		 /* r6 range [0..7] */
+	"r6 += 0x2;"		 /* r6 range [2..9] */
+	"r7 = 0;"
+	"r7 -= r6;"		 /* r7 range [-9..-2] */
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"r1 = r10;"
+	"r1 += r7;"
+	"r1 = *(u8 *)(r1 - 0);" /* touches slot [-16..-9] where spills are stored */
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("6: *(u64 *)(r10 -16) = r1")
+__xlated("...")
+__xlated("8: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("10: r1 = *(u64 *)(r10 -16)")
+__success
+__naked void bad_varying_write(void)
+{
+	asm volatile (
+	"r6 = *(u64 *)(r1 + 0);" /* random scalar value */
+	"r6 &= 0x7;"		 /* r6 range [0..7] */
+	"r6 += 0x2;"		 /* r6 range [2..9] */
+	"r7 = 0;"
+	"r7 -= r6;"		 /* r7 range [-9..-2] */
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"r1 = r10;"
+	"r1 += r7;"
+	"*(u8 *)(r1 - 0) = r7;" /* touches slot [-16..-9] where spills are stored */
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -8) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r1 = *(u64 *)(r10 -8)")
+__success
+__naked void bad_write_in_subprog(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"r1 = r10;"
+	"r1 += -8;"
+	"call bad_write_in_subprog_aux;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+__used
+__naked static void bad_write_in_subprog_aux(void)
+{
+	asm volatile (
+	"r0 = 1;"
+	"*(u64 *)(r1 - 0) = r0;"	/* invalidates bpf_fastcall contract for caller: */
+	"exit;"				/* caller stack at -8 used outside of the pattern */
+	::: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -8) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r1 = *(u64 *)(r10 -8)")
+__success
+__naked void bad_helper_write(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	/* bpf_fastcall pattern with stack offset -8 */
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"r1 = r10;"
+	"r1 += -8;"
+	"r2 = 1;"
+	"r3 = 42;"
+	/* read dst is fp[-8], thus bpf_fastcall rewrite not applied */
+	"call %[bpf_probe_read_kernel];"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id),
+	  __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+/* main, not patched */
+__xlated("1: *(u64 *)(r10 -8) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r1 = *(u64 *)(r10 -8)")
+__xlated("...")
+__xlated("9: call pc+1")
+__xlated("...")
+__xlated("10: exit")
+/* subprogram, patched */
+__xlated("11: r1 = 1")
+__xlated("...")
+__xlated("13: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("15: exit")
+__success
+__naked void invalidate_one_subprog(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"r1 = r10;"
+	"r1 += -8;"
+	"r1 = *(u64 *)(r1 - 0);"
+	"call invalidate_one_subprog_aux;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+__used
+__naked static void invalidate_one_subprog_aux(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+/* main */
+__xlated("0: r1 = 1")
+__xlated("...")
+__xlated("2: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("4: call pc+1")
+__xlated("5: exit")
+/* subprogram */
+__xlated("6: r1 = 1")
+__xlated("...")
+__xlated("8: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("10: *(u64 *)(r10 -16) = r1")
+__xlated("11: exit")
+__success
+__naked void subprogs_use_independent_offsets(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"call subprogs_use_independent_offsets_aux;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+__used
+__naked static void subprogs_use_independent_offsets_aux(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 24) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 24);"
+	"*(u64 *)(r10 - 16) = r1;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 8")
+__xlated("2: r0 = &(void __percpu *)(r0)")
+__success
+__naked void helper_call_does_not_prevent_bpf_fastcall(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_prandom_u32];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id),
+	  __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 16")
+/* may_goto counter at -16 */
+__xlated("0: *(u64 *)(r10 -16) =")
+__xlated("1: r1 = 1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+/* may_goto expansion starts */
+__xlated("5: r11 = *(u64 *)(r10 -16)")
+__xlated("6: if r11 == 0x0 goto pc+3")
+__xlated("7: r11 -= 1")
+__xlated("8: *(u64 *)(r10 -16) = r11")
+/* may_goto expansion ends */
+__xlated("9: *(u64 *)(r10 -8) = r1")
+__xlated("10: exit")
+__success
+__naked void may_goto_interaction(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	".8byte %[may_goto];"
+	/* just touch some stack at -8 */
+	"*(u64 *)(r10 - 8) = r1;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id),
+	  __imm_insn(may_goto, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, +1 /* offset */, 0))
+	: __clobber_all);
+}
+
+__used
+__naked static void dummy_loop_callback(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 32+0")
+__xlated("2: r1 = 1")
+__xlated("3: w0 =")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("5: r0 = *(u32 *)(r0 +0)")
+/* bpf_loop params setup */
+__xlated("6: r2 =")
+__xlated("7: r3 = 0")
+__xlated("8: r4 = 0")
+__xlated("...")
+/* ... part of the inlined bpf_loop */
+__xlated("12: *(u64 *)(r10 -32) = r6")
+__xlated("13: *(u64 *)(r10 -24) = r7")
+__xlated("14: *(u64 *)(r10 -16) = r8")
+__xlated("...")
+__xlated("21: call pc+8") /* dummy_loop_callback */
+/* ... last insns of the bpf_loop_interaction1 */
+__xlated("...")
+__xlated("28: r0 = 0")
+__xlated("29: exit")
+/* dummy_loop_callback */
+__xlated("30: r0 = 0")
+__xlated("31: exit")
+__success
+__naked int bpf_loop_interaction1(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	/* bpf_fastcall stack region at -16, but could be removed */
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"r2 = %[dummy_loop_callback];"
+	"r3 = 0;"
+	"r4 = 0;"
+	"call %[bpf_loop];"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_ptr(dummy_loop_callback),
+	  __imm(bpf_get_smp_processor_id),
+	  __imm(bpf_loop)
+	: __clobber_common
+	);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 40+0")
+/* call bpf_get_smp_processor_id */
+__xlated("2: r1 = 42")
+__xlated("3: w0 =")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("5: r0 = *(u32 *)(r0 +0)")
+/* call bpf_get_prandom_u32 */
+__xlated("6: *(u64 *)(r10 -16) = r1")
+__xlated("7: call")
+__xlated("8: r1 = *(u64 *)(r10 -16)")
+__xlated("...")
+/* ... part of the inlined bpf_loop */
+__xlated("15: *(u64 *)(r10 -40) = r6")
+__xlated("16: *(u64 *)(r10 -32) = r7")
+__xlated("17: *(u64 *)(r10 -24) = r8")
+__success
+__naked int bpf_loop_interaction2(void)
+{
+	asm volatile (
+	"r1 = 42;"
+	/* bpf_fastcall stack region at -16, cannot be removed */
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_prandom_u32];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"r2 = %[dummy_loop_callback];"
+	"r3 = 0;"
+	"r4 = 0;"
+	"call %[bpf_loop];"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_ptr(dummy_loop_callback),
+	  __imm(bpf_get_smp_processor_id),
+	  __imm(bpf_get_prandom_u32),
+	  __imm(bpf_loop)
+	: __clobber_common
+	);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4)
+__msg("stack depth 512+0")
+/* just to print xlated version when debugging */
+__xlated("r0 = &(void __percpu *)(r0)")
+__success
+/* cumulative_stack_depth() stack usage is MAX_BPF_STACK,
+ * called subprogram uses an additional slot for bpf_fastcall spill/fill,
+ * since bpf_fastcall spill/fill could be removed the program still fits
+ * in MAX_BPF_STACK and should be accepted.
+ */
+__naked int cumulative_stack_depth(void)
+{
+	asm volatile(
+	"r1 = 42;"
+	"*(u64 *)(r10 - %[max_bpf_stack]) = r1;"
+	"call cumulative_stack_depth_subprog;"
+	"exit;"
+	:
+	: __imm_const(max_bpf_stack, MAX_BPF_STACK)
+	: __clobber_all
+	);
+}
+
+__used
+__naked static void cumulative_stack_depth_subprog(void)
+{
+	asm volatile (
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"exit;"
+	:: __imm(bpf_get_smp_processor_id) : __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4)
+__msg("stack depth 512")
+__xlated("0: r1 = 42")
+__xlated("1: *(u64 *)(r10 -512) = r1")
+__xlated("2: w0 = ")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("4: r0 = *(u32 *)(r0 +0)")
+__xlated("5: exit")
+__success
+__naked int bpf_fastcall_max_stack_ok(void)
+{
+	asm volatile(
+	"r1 = 42;"
+	"*(u64 *)(r10 - %[max_bpf_stack]) = r1;"
+	"*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);"
+	"exit;"
+	:
+	: __imm_const(max_bpf_stack, MAX_BPF_STACK),
+	  __imm_const(max_bpf_stack_8, MAX_BPF_STACK + 8),
+	  __imm(bpf_get_smp_processor_id)
+	: __clobber_all
+	);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4)
+__msg("stack depth 520")
+__failure
+__naked int bpf_fastcall_max_stack_fail(void)
+{
+	asm volatile(
+	"r1 = 42;"
+	"*(u64 *)(r10 - %[max_bpf_stack]) = r1;"
+	"*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);"
+	/* call to prandom blocks bpf_fastcall rewrite */
+	"*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;"
+	"call %[bpf_get_prandom_u32];"
+	"r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);"
+	"exit;"
+	:
+	: __imm_const(max_bpf_stack, MAX_BPF_STACK),
+	  __imm_const(max_bpf_stack_8, MAX_BPF_STACK + 8),
+	  __imm(bpf_get_smp_processor_id),
+	  __imm(bpf_get_prandom_u32)
+	: __clobber_all
+	);
+}
+
+SEC("cgroup/getsockname_unix")
+__xlated("0: r2 = 1")
+/* bpf_cast_to_kern_ctx is replaced by a single assignment */
+__xlated("1: r0 = r1")
+__xlated("2: r0 = r2")
+__xlated("3: exit")
+__success
+__naked void kfunc_bpf_cast_to_kern_ctx(void)
+{
+	asm volatile (
+	"r2 = 1;"
+	"*(u64 *)(r10 - 32) = r2;"
+	"call %[bpf_cast_to_kern_ctx];"
+	"r2 = *(u64 *)(r10 - 32);"
+	"r0 = r2;"
+	"exit;"
+	:
+	: __imm(bpf_cast_to_kern_ctx)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__xlated("3: r3 = 1")
+/* bpf_rdonly_cast is replaced by a single assignment */
+__xlated("4: r0 = r1")
+__xlated("5: r0 = r3")
+void kfunc_bpf_rdonly_cast(void)
+{
+	asm volatile (
+	"r2 = %[btf_id];"
+	"r3 = 1;"
+	"*(u64 *)(r10 - 32) = r3;"
+	"call %[bpf_rdonly_cast];"
+	"r3 = *(u64 *)(r10 - 32);"
+	"r0 = r3;"
+	:
+	: __imm(bpf_rdonly_cast),
+	 [btf_id]"r"(bpf_core_type_id_kernel(union bpf_attr))
+	: __clobber_common);
+}
+
+/* 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 kfunc_root(void)
+{
+	bpf_cast_to_kern_ctx(0);
+	bpf_rdonly_cast(0, 0);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_const.c b/tools/testing/selftests/bpf/progs/verifier_const.c
new file mode 100644
index 000000000000..2e533d7eec2f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_const.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Isovalent */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+const volatile long foo = 42;
+long bar;
+long bart = 96;
+
+SEC("tc/ingress")
+__description("rodata/strtol: write rejected")
+__failure __msg("write into map forbidden")
+int tcx1(struct __sk_buff *skb)
+{
+	char buff[] = { '8', '4', '\0' };
+	bpf_strtol(buff, sizeof(buff), 0, (long *)&foo);
+	return TCX_PASS;
+}
+
+SEC("tc/ingress")
+__description("bss/strtol: write accepted")
+__success
+int tcx2(struct __sk_buff *skb)
+{
+	char buff[] = { '8', '4', '\0' };
+	bpf_strtol(buff, sizeof(buff), 0, &bar);
+	return TCX_PASS;
+}
+
+SEC("tc/ingress")
+__description("data/strtol: write accepted")
+__success
+int tcx3(struct __sk_buff *skb)
+{
+	char buff[] = { '8', '4', '\0' };
+	bpf_strtol(buff, sizeof(buff), 0, &bart);
+	return TCX_PASS;
+}
+
+SEC("tc/ingress")
+__description("rodata/mtu: write rejected")
+__failure __msg("write into map forbidden")
+int tcx4(struct __sk_buff *skb)
+{
+	bpf_check_mtu(skb, skb->ifindex, (__u32 *)&foo, 0, 0);
+	return TCX_PASS;
+}
+
+SEC("tc/ingress")
+__description("bss/mtu: write accepted")
+__success
+int tcx5(struct __sk_buff *skb)
+{
+	bpf_check_mtu(skb, skb->ifindex, (__u32 *)&bar, 0, 0);
+	return TCX_PASS;
+}
+
+SEC("tc/ingress")
+__description("data/mtu: write accepted")
+__success
+int tcx6(struct __sk_buff *skb)
+{
+	bpf_check_mtu(skb, skb->ifindex, (__u32 *)&bart, 0, 0);
+	return TCX_PASS;
+}
+
+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 a9fc30ed4d73..20904cd2baa2 100644
--- a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
+++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
@@ -7,6 +7,7 @@
 #include "bpf_misc.h"
 #include "xdp_metadata.h"
 #include "bpf_kfuncs.h"
+#include "err.h"
 
 /* The compiler may be able to detect the access to uninitialized
    memory in the routines performing out of bound memory accesses and
@@ -331,7 +332,11 @@ SEC("?lsm/bpf")
 __success __log_level(2)
 int BPF_PROG(arg_tag_ctx_lsm)
 {
-	return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+	int ret;
+
+	ret = tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+	set_if_not_errno_or_zero(ret, -1);
+	return ret;
 }
 
 SEC("?struct_ops/test_1")
diff --git a/tools/testing/selftests/bpf/progs/verifier_int_ptr.c b/tools/testing/selftests/bpf/progs/verifier_int_ptr.c
index 9fc3fae5cd83..5f2efb895edb 100644
--- a/tools/testing/selftests/bpf/progs/verifier_int_ptr.c
+++ b/tools/testing/selftests/bpf/progs/verifier_int_ptr.c
@@ -6,9 +6,8 @@
 #include "bpf_misc.h"
 
 SEC("socket")
-__description("ARG_PTR_TO_LONG uninitialized")
+__description("arg pointer to long uninitialized")
 __success
-__failure_unpriv __msg_unpriv("invalid indirect read from stack R4 off -16+0 size 8")
 __naked void arg_ptr_to_long_uninitialized(void)
 {
 	asm volatile ("					\
@@ -35,10 +34,8 @@ __naked void arg_ptr_to_long_uninitialized(void)
 }
 
 SEC("socket")
-__description("ARG_PTR_TO_LONG half-uninitialized")
-/* in privileged mode reads from uninitialized stack locations are permitted */
-__success __failure_unpriv
-__msg_unpriv("invalid indirect read from stack R4 off -16+4 size 8")
+__description("arg pointer to long half-uninitialized")
+__success
 __retval(0)
 __naked void ptr_to_long_half_uninitialized(void)
 {
@@ -67,7 +64,7 @@ __naked void ptr_to_long_half_uninitialized(void)
 }
 
 SEC("cgroup/sysctl")
-__description("ARG_PTR_TO_LONG misaligned")
+__description("arg pointer to long misaligned")
 __failure __msg("misaligned stack access off 0+-20+0 size 8")
 __naked void arg_ptr_to_long_misaligned(void)
 {
@@ -98,7 +95,7 @@ __naked void arg_ptr_to_long_misaligned(void)
 }
 
 SEC("cgroup/sysctl")
-__description("ARG_PTR_TO_LONG size < sizeof(long)")
+__description("arg pointer to long size < sizeof(long)")
 __failure __msg("invalid indirect access to stack R4 off=-4 size=8")
 __naked void to_long_size_sizeof_long(void)
 {
@@ -127,7 +124,7 @@ __naked void to_long_size_sizeof_long(void)
 }
 
 SEC("cgroup/sysctl")
-__description("ARG_PTR_TO_LONG initialized")
+__description("arg pointer to long initialized")
 __success
 __naked void arg_ptr_to_long_initialized(void)
 {
diff --git a/tools/testing/selftests/bpf/progs/verifier_jit_convergence.c b/tools/testing/selftests/bpf/progs/verifier_jit_convergence.c
new file mode 100644
index 000000000000..9f3f2b7db450
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_jit_convergence.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct value_t {
+	long long a[32];
+};
+
+struct {
+        __uint(type, BPF_MAP_TYPE_HASH);
+        __uint(max_entries, 1);
+        __type(key, long long);
+        __type(value, struct value_t);
+} map_hash SEC(".maps");
+
+SEC("socket")
+__description("bpf_jit_convergence je <-> jmp")
+__success __retval(0)
+__arch_x86_64
+__jited("	pushq	%rbp")
+__naked void btf_jit_convergence_je_jmp(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"if r0 == 0 goto l20_%=;"
+	"if r0 == 1 goto l21_%=;"
+	"if r0 == 2 goto l22_%=;"
+	"if r0 == 3 goto l23_%=;"
+	"if r0 == 4 goto l24_%=;"
+	"call %[bpf_get_prandom_u32];"
+	"call %[bpf_get_prandom_u32];"
+"l20_%=:"
+"l21_%=:"
+"l22_%=:"
+"l23_%=:"
+"l24_%=:"
+	"r1 = 0;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = r10;"
+	"r2 += -8;"
+	"r1 = %[map_hash] ll;"
+	"call %[bpf_map_lookup_elem];"
+	"if r0 == 0 goto l1_%=;"
+	"r6 = r0;"
+	"call %[bpf_get_prandom_u32];"
+	"r7 = r0;"
+	"r5 = r6;"
+	"if r0 != 0x0 goto l12_%=;"
+	"call %[bpf_get_prandom_u32];"
+	"r1 = r0;"
+	"r2 = r6;"
+	"if r1 == 0x0 goto l0_%=;"
+"l9_%=:"
+	"r2 = *(u64 *)(r6 + 0x0);"
+	"r2 += 0x1;"
+	"*(u64 *)(r6 + 0x0) = r2;"
+	"goto l1_%=;"
+"l12_%=:"
+	"r1 = r7;"
+	"r1 += 0x98;"
+	"r2 = r5;"
+	"r2 += 0x90;"
+	"r2 = *(u32 *)(r2 + 0x0);"
+	"r3 = r7;"
+	"r3 &= 0x1;"
+	"r2 *= 0xa8;"
+	"if r3 == 0x0 goto l2_%=;"
+	"r1 += r2;"
+	"r1 -= r7;"
+	"r1 += 0x8;"
+	"if r1 <= 0xb20 goto l3_%=;"
+	"r1 = 0x0;"
+	"goto l4_%=;"
+"l3_%=:"
+	"r1 += r7;"
+"l4_%=:"
+	"if r1 == 0x0 goto l8_%=;"
+	"goto l9_%=;"
+"l2_%=:"
+	"r1 += r2;"
+	"r1 -= r7;"
+	"r1 += 0x10;"
+	"if r1 <= 0xb20 goto l6_%=;"
+	"r1 = 0x0;"
+	"goto l7_%=;"
+"l6_%=:"
+	"r1 += r7;"
+"l7_%=:"
+	"if r1 == 0x0 goto l8_%=;"
+	"goto l9_%=;"
+"l0_%=:"
+	"r1 = 0x3;"
+	"*(u64 *)(r10 - 0x10) = r1;"
+	"r2 = r1;"
+	"goto l1_%=;"
+"l8_%=:"
+	"r1 = r5;"
+	"r1 += 0x4;"
+	"r1 = *(u32 *)(r1 + 0x0);"
+	"*(u64 *)(r10 - 0x8) = r1;"
+"l1_%=:"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_kfunc_prog_types.c b/tools/testing/selftests/bpf/progs/verifier_kfunc_prog_types.c
index cb32b0cfc84b..a509cad97e69 100644
--- a/tools/testing/selftests/bpf/progs/verifier_kfunc_prog_types.c
+++ b/tools/testing/selftests/bpf/progs/verifier_kfunc_prog_types.c
@@ -47,6 +47,22 @@ int BPF_PROG(task_kfunc_syscall)
 	return 0;
 }
 
+SEC("tracepoint")
+__success
+int BPF_PROG(task_kfunc_tracepoint)
+{
+	task_kfunc_load_test();
+	return 0;
+}
+
+SEC("perf_event")
+__success
+int BPF_PROG(task_kfunc_perf_event)
+{
+	task_kfunc_load_test();
+	return 0;
+}
+
 /*****************
  * cgroup kfuncs *
  *****************/
@@ -85,6 +101,22 @@ int BPF_PROG(cgrp_kfunc_syscall)
 	return 0;
 }
 
+SEC("tracepoint")
+__success
+int BPF_PROG(cgrp_kfunc_tracepoint)
+{
+	cgrp_kfunc_load_test();
+	return 0;
+}
+
+SEC("perf_event")
+__success
+int BPF_PROG(cgrp_kfunc_perf_event)
+{
+	cgrp_kfunc_load_test();
+	return 0;
+}
+
 /******************
  * cpumask kfuncs *
  ******************/
@@ -120,3 +152,19 @@ int BPF_PROG(cpumask_kfunc_syscall)
 	cpumask_kfunc_load_test();
 	return 0;
 }
+
+SEC("tracepoint")
+__success
+int BPF_PROG(cpumask_kfunc_tracepoint)
+{
+	cpumask_kfunc_load_test();
+	return 0;
+}
+
+SEC("perf_event")
+__success
+int BPF_PROG(cpumask_kfunc_perf_event)
+{
+	cpumask_kfunc_load_test();
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
index d4427d8e1217..52edee41caf6 100644
--- a/tools/testing/selftests/bpf/progs/verifier_ldsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
@@ -144,6 +144,118 @@ __naked void ldsx_s32_range(void)
 	: __clobber_all);
 }
 
+SEC("xdp")
+__description("LDSX, xdp s32 xdp_md->data")
+__failure __msg("invalid bpf_context access")
+__naked void ldsx_ctx_1(void)
+{
+	asm volatile (
+	"r2 = *(s32 *)(r1 + %[xdp_md_data]);"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("LDSX, xdp s32 xdp_md->data_end")
+__failure __msg("invalid bpf_context access")
+__naked void ldsx_ctx_2(void)
+{
+	asm volatile (
+	"r2 = *(s32 *)(r1 + %[xdp_md_data_end]);"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("LDSX, xdp s32 xdp_md->data_meta")
+__failure __msg("invalid bpf_context access")
+__naked void ldsx_ctx_3(void)
+{
+	asm volatile (
+	"r2 = *(s32 *)(r1 + %[xdp_md_data_meta]);"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("tcx/ingress")
+__description("LDSX, tcx s32 __sk_buff->data")
+__failure __msg("invalid bpf_context access")
+__naked void ldsx_ctx_4(void)
+{
+	asm volatile (
+	"r2 = *(s32 *)(r1 + %[sk_buff_data]);"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(sk_buff_data, offsetof(struct __sk_buff, data))
+	: __clobber_all);
+}
+
+SEC("tcx/ingress")
+__description("LDSX, tcx s32 __sk_buff->data_end")
+__failure __msg("invalid bpf_context access")
+__naked void ldsx_ctx_5(void)
+{
+	asm volatile (
+	"r2 = *(s32 *)(r1 + %[sk_buff_data_end]);"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tcx/ingress")
+__description("LDSX, tcx s32 __sk_buff->data_meta")
+__failure __msg("invalid bpf_context access")
+__naked void ldsx_ctx_6(void)
+{
+	asm volatile (
+	"r2 = *(s32 *)(r1 + %[sk_buff_data_meta]);"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(sk_buff_data_meta, offsetof(struct __sk_buff, data_meta))
+	: __clobber_all);
+}
+
+SEC("flow_dissector")
+__description("LDSX, flow_dissector s32 __sk_buff->data")
+__failure __msg("invalid bpf_context access")
+__naked void ldsx_ctx_7(void)
+{
+	asm volatile (
+	"r2 = *(s32 *)(r1 + %[sk_buff_data]);"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(sk_buff_data, offsetof(struct __sk_buff, data))
+	: __clobber_all);
+}
+
+SEC("flow_dissector")
+__description("LDSX, flow_dissector s32 __sk_buff->data_end")
+__failure __msg("invalid bpf_context access")
+__naked void ldsx_ctx_8(void)
+{
+	asm volatile (
+	"r2 = *(s32 *)(r1 + %[sk_buff_data_end]);"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
 #else
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_lsm.c b/tools/testing/selftests/bpf/progs/verifier_lsm.c
new file mode 100644
index 000000000000..32e5e779cb96
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_lsm.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("lsm/file_alloc_security")
+__description("lsm bpf prog with -4095~0 retval. test 1")
+__success
+__naked int errno_zero_retval_test1(void *ctx)
+{
+	asm volatile (
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/file_alloc_security")
+__description("lsm bpf prog with -4095~0 retval. test 2")
+__success
+__naked int errno_zero_retval_test2(void *ctx)
+{
+	asm volatile (
+	"r0 = -4095;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/file_mprotect")
+__description("lsm bpf prog with -4095~0 retval. test 4")
+__failure __msg("R0 has smin=-4096 smax=-4096 should have been in [-4095, 0]")
+__naked int errno_zero_retval_test4(void *ctx)
+{
+	asm volatile (
+	"r0 = -4096;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/file_mprotect")
+__description("lsm bpf prog with -4095~0 retval. test 5")
+__failure __msg("R0 has smin=4096 smax=4096 should have been in [-4095, 0]")
+__naked int errno_zero_retval_test5(void *ctx)
+{
+	asm volatile (
+	"r0 = 4096;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/file_mprotect")
+__description("lsm bpf prog with -4095~0 retval. test 6")
+__failure __msg("R0 has smin=1 smax=1 should have been in [-4095, 0]")
+__naked int errno_zero_retval_test6(void *ctx)
+{
+	asm volatile (
+	"r0 = 1;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/audit_rule_known")
+__description("lsm bpf prog with bool retval. test 1")
+__success
+__naked int bool_retval_test1(void *ctx)
+{
+	asm volatile (
+	"r0 = 1;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/audit_rule_known")
+__description("lsm bpf prog with bool retval. test 2")
+__success
+__success
+__naked int bool_retval_test2(void *ctx)
+{
+	asm volatile (
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/audit_rule_known")
+__description("lsm bpf prog with bool retval. test 3")
+__failure __msg("R0 has smin=-1 smax=-1 should have been in [0, 1]")
+__naked int bool_retval_test3(void *ctx)
+{
+	asm volatile (
+	"r0 = -1;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/audit_rule_known")
+__description("lsm bpf prog with bool retval. test 4")
+__failure __msg("R0 has smin=2 smax=2 should have been in [0, 1]")
+__naked int bool_retval_test4(void *ctx)
+{
+	asm volatile (
+	"r0 = 2;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/file_free_security")
+__success
+__description("lsm bpf prog with void retval. test 1")
+__naked int void_retval_test1(void *ctx)
+{
+	asm volatile (
+	"r0 = -4096;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/file_free_security")
+__success
+__description("lsm bpf prog with void retval. test 2")
+__naked int void_retval_test2(void *ctx)
+{
+	asm volatile (
+	"r0 = 4096;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/getprocattr")
+__description("lsm disabled hook: getprocattr")
+__failure __msg("points to disabled hook")
+__naked int disabled_hook_test1(void *ctx)
+{
+	asm volatile (
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/setprocattr")
+__description("lsm disabled hook: setprocattr")
+__failure __msg("points to disabled hook")
+__naked int disabled_hook_test2(void *ctx)
+{
+	asm volatile (
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/ismaclabel")
+__description("lsm disabled hook: ismaclabel")
+__failure __msg("points to disabled hook")
+__naked int disabled_hook_test3(void *ctx)
+{
+	asm volatile (
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
index 13b29a7faa71..2ecf77b623e0 100644
--- a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
+++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
@@ -5,18 +5,27 @@
 #include "bpf_misc.h"
 
 /* Check that precision marks propagate through scalar IDs.
- * Registers r{0,1,2} have the same scalar ID at the moment when r0 is
- * marked to be precise, this mark is immediately propagated to r{1,2}.
+ * Registers r{0,1,2} have the same scalar ID.
+ * Range information is propagated for scalars sharing same ID.
+ * Check that precision mark for r0 causes precision marks for r{1,2}
+ * when range information is propagated for 'if <reg> <op> <const>' insn.
  */
 SEC("socket")
 __success __log_level(2)
-__msg("frame0: regs=r0,r1,r2 stack= before 4: (bf) r3 = r10")
+/* first 'if' branch */
+__msg("6: (0f) r3 += r0")
+__msg("frame0: regs=r0 stack= before 4: (25) if r1 > 0x7 goto pc+0")
+__msg("frame0: parent state regs=r0,r1,r2 stack=:")
 __msg("frame0: regs=r0,r1,r2 stack= before 3: (bf) r2 = r0")
-__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0")
-__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255")
-__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns")
+/* second 'if' branch */
+__msg("from 4 to 5: ")
+__msg("6: (0f) r3 += r0")
+__msg("frame0: regs=r0 stack= before 5: (bf) r3 = r10")
+__msg("frame0: regs=r0 stack= before 4: (25) if r1 > 0x7 goto pc+0")
+/* parent state already has r{0,1,2} as precise */
+__msg("frame0: parent state regs= stack=:")
 __flag(BPF_F_TEST_STATE_FREQ)
-__naked void precision_same_state(void)
+__naked void linked_regs_bpf_k(void)
 {
 	asm volatile (
 	/* r0 = random number up to 0xff */
@@ -25,7 +34,8 @@ __naked void precision_same_state(void)
 	/* tie r0.id == r1.id == r2.id */
 	"r1 = r0;"
 	"r2 = r0;"
-	/* force r0 to be precise, this immediately marks r1 and r2 as
+	"if r1 > 7 goto +0;"
+	/* force r0 to be precise, this eventually marks r1 and r2 as
 	 * precise as well because of shared IDs
 	 */
 	"r3 = r10;"
@@ -37,22 +47,17 @@ __naked void precision_same_state(void)
 	: __clobber_all);
 }
 
-/* Same as precision_same_state, but mark propagates through state /
- * parent state boundary.
+/* Registers r{0,1,2} share same ID when 'if r1 > ...' insn is processed,
+ * check that verifier marks r{1,2} as precise while backtracking
+ * 'if r1 > ...' with r0 already marked.
  */
 SEC("socket")
 __success __log_level(2)
-__msg("frame0: last_idx 6 first_idx 5 subseq_idx -1")
-__msg("frame0: regs=r0,r1,r2 stack= before 5: (bf) r3 = r10")
-__msg("frame0: parent state regs=r0,r1,r2 stack=:")
-__msg("frame0: regs=r0,r1,r2 stack= before 4: (05) goto pc+0")
-__msg("frame0: regs=r0,r1,r2 stack= before 3: (bf) r2 = r0")
-__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0")
-__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255")
-__msg("frame0: parent state regs=r0 stack=:")
-__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns")
 __flag(BPF_F_TEST_STATE_FREQ)
-__naked void precision_cross_state(void)
+__msg("frame0: regs=r0 stack= before 5: (2d) if r1 > r3 goto pc+0")
+__msg("frame0: parent state regs=r0,r1,r2,r3 stack=:")
+__msg("frame0: regs=r0,r1,r2,r3 stack= before 4: (b7) r3 = 7")
+__naked void linked_regs_bpf_x_src(void)
 {
 	asm volatile (
 	/* r0 = random number up to 0xff */
@@ -61,13 +66,13 @@ __naked void precision_cross_state(void)
 	/* tie r0.id == r1.id == r2.id */
 	"r1 = r0;"
 	"r2 = r0;"
-	/* force checkpoint */
-	"goto +0;"
-	/* force r0 to be precise, this immediately marks r1 and r2 as
+	"r3 = 7;"
+	"if r1 > r3 goto +0;"
+	/* force r0 to be precise, this eventually marks r1 and r2 as
 	 * precise as well because of shared IDs
 	 */
-	"r3 = r10;"
-	"r3 += r0;"
+	"r4 = r10;"
+	"r4 += r0;"
 	"r0 = 0;"
 	"exit;"
 	:
@@ -75,19 +80,17 @@ __naked void precision_cross_state(void)
 	: __clobber_all);
 }
 
-/* Same as precision_same_state, but break one of the
- * links, note that r1 is absent from regs=... in __msg below.
+/* Registers r{0,1,2} share same ID when 'if r1 > r3' insn is processed,
+ * check that verifier marks r{0,1,2} as precise while backtracking
+ * 'if r1 > r3' with r3 already marked.
  */
 SEC("socket")
 __success __log_level(2)
-__msg("frame0: regs=r0,r2 stack= before 5: (bf) r3 = r10")
-__msg("frame0: regs=r0,r2 stack= before 4: (b7) r1 = 0")
-__msg("frame0: regs=r0,r2 stack= before 3: (bf) r2 = r0")
-__msg("frame0: regs=r0 stack= before 2: (bf) r1 = r0")
-__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255")
-__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns")
 __flag(BPF_F_TEST_STATE_FREQ)
-__naked void precision_same_state_broken_link(void)
+__msg("frame0: regs=r3 stack= before 5: (2d) if r1 > r3 goto pc+0")
+__msg("frame0: parent state regs=r0,r1,r2,r3 stack=:")
+__msg("frame0: regs=r0,r1,r2,r3 stack= before 4: (b7) r3 = 7")
+__naked void linked_regs_bpf_x_dst(void)
 {
 	asm volatile (
 	/* r0 = random number up to 0xff */
@@ -96,15 +99,13 @@ __naked void precision_same_state_broken_link(void)
 	/* tie r0.id == r1.id == r2.id */
 	"r1 = r0;"
 	"r2 = r0;"
-	/* break link for r1, this is the only line that differs
-	 * compared to the previous test
-	 */
-	"r1 = 0;"
-	/* force r0 to be precise, this immediately marks r1 and r2 as
+	"r3 = 7;"
+	"if r1 > r3 goto +0;"
+	/* force r0 to be precise, this eventually marks r1 and r2 as
 	 * precise as well because of shared IDs
 	 */
-	"r3 = r10;"
-	"r3 += r0;"
+	"r4 = r10;"
+	"r4 += r3;"
 	"r0 = 0;"
 	"exit;"
 	:
@@ -112,22 +113,18 @@ __naked void precision_same_state_broken_link(void)
 	: __clobber_all);
 }
 
-/* Same as precision_same_state_broken_link, but with state /
- * parent state boundary.
+/* Same as linked_regs_bpf_k, but break one of the
+ * links, note that r1 is absent from regs=... in __msg below.
  */
 SEC("socket")
 __success __log_level(2)
-__msg("frame0: regs=r0,r2 stack= before 6: (bf) r3 = r10")
-__msg("frame0: regs=r0,r2 stack= before 5: (b7) r1 = 0")
-__msg("frame0: parent state regs=r0,r2 stack=:")
-__msg("frame0: regs=r0,r1,r2 stack= before 4: (05) goto pc+0")
-__msg("frame0: regs=r0,r1,r2 stack= before 3: (bf) r2 = r0")
-__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0")
-__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255")
+__msg("7: (0f) r3 += r0")
+__msg("frame0: regs=r0 stack= before 6: (bf) r3 = r10")
 __msg("frame0: parent state regs=r0 stack=:")
-__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns")
+__msg("frame0: regs=r0 stack= before 5: (25) if r0 > 0x7 goto pc+0")
+__msg("frame0: parent state regs=r0,r2 stack=:")
 __flag(BPF_F_TEST_STATE_FREQ)
-__naked void precision_cross_state_broken_link(void)
+__naked void linked_regs_broken_link(void)
 {
 	asm volatile (
 	/* r0 = random number up to 0xff */
@@ -136,18 +133,13 @@ __naked void precision_cross_state_broken_link(void)
 	/* tie r0.id == r1.id == r2.id */
 	"r1 = r0;"
 	"r2 = r0;"
-	/* force checkpoint, although link between r1 and r{0,2} is
-	 * broken by the next statement current precision tracking
-	 * algorithm can't react to it and propagates mark for r1 to
-	 * the parent state.
-	 */
-	"goto +0;"
 	/* break link for r1, this is the only line that differs
-	 * compared to precision_cross_state()
+	 * compared to the previous test
 	 */
 	"r1 = 0;"
-	/* force r0 to be precise, this immediately marks r1 and r2 as
-	 * precise as well because of shared IDs
+	"if r0 > 7 goto +0;"
+	/* force r0 to be precise,
+	 * this eventually marks r2 as precise because of shared IDs
 	 */
 	"r3 = r10;"
 	"r3 += r0;"
@@ -164,10 +156,16 @@ __naked void precision_cross_state_broken_link(void)
  */
 SEC("socket")
 __success __log_level(2)
-__msg("11: (0f) r2 += r1")
+__msg("12: (0f) r2 += r1")
 /* Current state */
-__msg("frame2: last_idx 11 first_idx 10 subseq_idx -1")
-__msg("frame2: regs=r1 stack= before 10: (bf) r2 = r10")
+__msg("frame2: last_idx 12 first_idx 11 subseq_idx -1 ")
+__msg("frame2: regs=r1 stack= before 11: (bf) r2 = r10")
+__msg("frame2: parent state regs=r1 stack=")
+__msg("frame1: parent state regs= stack=")
+__msg("frame0: parent state regs= stack=")
+/* Parent state */
+__msg("frame2: last_idx 10 first_idx 10 subseq_idx 11 ")
+__msg("frame2: regs=r1 stack= before 10: (25) if r1 > 0x7 goto pc+0")
 __msg("frame2: parent state regs=r1 stack=")
 /* frame1.r{6,7} are marked because mark_precise_scalar_ids()
  * looks for all registers with frame2.r1.id in the current state
@@ -192,7 +190,7 @@ __msg("frame1: regs=r1 stack= before 4: (85) call pc+1")
 __msg("frame0: parent state regs=r1,r6 stack=")
 /* Parent state */
 __msg("frame0: last_idx 3 first_idx 1 subseq_idx 4")
-__msg("frame0: regs=r0,r1,r6 stack= before 3: (bf) r6 = r0")
+__msg("frame0: regs=r1,r6 stack= before 3: (bf) r6 = r0")
 __msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0")
 __msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255")
 __flag(BPF_F_TEST_STATE_FREQ)
@@ -230,7 +228,8 @@ static __naked __noinline __used
 void precision_many_frames__bar(void)
 {
 	asm volatile (
-	/* force r1 to be precise, this immediately marks:
+	"if r1 > 7 goto +0;"
+	/* force r1 to be precise, this eventually marks:
 	 * - bar frame r1
 	 * - foo frame r{1,6,7}
 	 * - main frame r{1,6}
@@ -247,14 +246,16 @@ void precision_many_frames__bar(void)
  */
 SEC("socket")
 __success __log_level(2)
+__msg("11: (0f) r2 += r1")
 /* foo frame */
-__msg("frame1: regs=r1 stack=-8,-16 before 9: (bf) r2 = r10")
+__msg("frame1: regs=r1 stack= before 10: (bf) r2 = r10")
+__msg("frame1: regs=r1 stack= before 9: (25) if r1 > 0x7 goto pc+0")
 __msg("frame1: regs=r1 stack=-8,-16 before 8: (7b) *(u64 *)(r10 -16) = r1")
 __msg("frame1: regs=r1 stack=-8 before 7: (7b) *(u64 *)(r10 -8) = r1")
 __msg("frame1: regs=r1 stack= before 4: (85) call pc+2")
 /* main frame */
-__msg("frame0: regs=r0,r1 stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r1")
-__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0")
+__msg("frame0: regs=r1 stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r1")
+__msg("frame0: regs=r1 stack= before 2: (bf) r1 = r0")
 __msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255")
 __flag(BPF_F_TEST_STATE_FREQ)
 __naked void precision_stack(void)
@@ -283,7 +284,8 @@ void precision_stack__foo(void)
 	 */
 	"*(u64*)(r10 - 8) = r1;"
 	"*(u64*)(r10 - 16) = r1;"
-	/* force r1 to be precise, this immediately marks:
+	"if r1 > 7 goto +0;"
+	/* force r1 to be precise, this eventually marks:
 	 * - foo frame r1,fp{-8,-16}
 	 * - main frame r1,fp{-8}
 	 */
@@ -299,15 +301,17 @@ void precision_stack__foo(void)
 SEC("socket")
 __success __log_level(2)
 /* r{6,7} */
-__msg("11: (0f) r3 += r7")
-__msg("frame0: regs=r6,r7 stack= before 10: (bf) r3 = r10")
+__msg("12: (0f) r3 += r7")
+__msg("frame0: regs=r7 stack= before 11: (bf) r3 = r10")
+__msg("frame0: regs=r7 stack= before 9: (25) if r7 > 0x7 goto pc+0")
 /* ... skip some insns ... */
 __msg("frame0: regs=r6,r7 stack= before 3: (bf) r7 = r0")
 __msg("frame0: regs=r0,r6 stack= before 2: (bf) r6 = r0")
 /* r{8,9} */
-__msg("12: (0f) r3 += r9")
-__msg("frame0: regs=r8,r9 stack= before 11: (0f) r3 += r7")
+__msg("13: (0f) r3 += r9")
+__msg("frame0: regs=r9 stack= before 12: (0f) r3 += r7")
 /* ... skip some insns ... */
+__msg("frame0: regs=r9 stack= before 10: (25) if r9 > 0x7 goto pc+0")
 __msg("frame0: regs=r8,r9 stack= before 7: (bf) r9 = r0")
 __msg("frame0: regs=r0,r8 stack= before 6: (bf) r8 = r0")
 __flag(BPF_F_TEST_STATE_FREQ)
@@ -328,8 +332,9 @@ __naked void precision_two_ids(void)
 	"r9 = r0;"
 	/* clear r0 id */
 	"r0 = 0;"
-	/* force checkpoint */
-	"goto +0;"
+	/* propagate equal scalars precision */
+	"if r7 > 7 goto +0;"
+	"if r9 > 7 goto +0;"
 	"r3 = r10;"
 	/* force r7 to be precise, this also marks r6 */
 	"r3 += r7;"
@@ -341,6 +346,105 @@ __naked void precision_two_ids(void)
 	: __clobber_all);
 }
 
+SEC("socket")
+__success __log_level(2)
+__flag(BPF_F_TEST_STATE_FREQ)
+/* check thar r0 and r6 have different IDs after 'if',
+ * collect_linked_regs() can't tie more than 6 registers for a single insn.
+ */
+__msg("8: (25) if r0 > 0x7 goto pc+0         ; R0=scalar(id=1")
+__msg("9: (bf) r6 = r6                       ; R6_w=scalar(id=2")
+/* check that r{0-5} are marked precise after 'if' */
+__msg("frame0: regs=r0 stack= before 8: (25) if r0 > 0x7 goto pc+0")
+__msg("frame0: parent state regs=r0,r1,r2,r3,r4,r5 stack=:")
+__naked void linked_regs_too_many_regs(void)
+{
+	asm volatile (
+	/* r0 = random number up to 0xff */
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	/* tie r{0-6} IDs */
+	"r1 = r0;"
+	"r2 = r0;"
+	"r3 = r0;"
+	"r4 = r0;"
+	"r5 = r0;"
+	"r6 = r0;"
+	/* propagate range for r{0-6} */
+	"if r0 > 7 goto +0;"
+	/* make r6 appear in the log */
+	"r6 = r6;"
+	/* force r0 to be precise,
+	 * this would cause r{0-4} to be precise because of shared IDs
+	 */
+	"r7 = r10;"
+	"r7 += r0;"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__failure __log_level(2)
+__flag(BPF_F_TEST_STATE_FREQ)
+__msg("regs=r7 stack= before 5: (3d) if r8 >= r0")
+__msg("parent state regs=r0,r7,r8")
+__msg("regs=r0,r7,r8 stack= before 4: (25) if r0 > 0x1")
+__msg("div by zero")
+__naked void linked_regs_broken_link_2(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"r7 = r0;"
+	"r8 = r0;"
+	"call %[bpf_get_prandom_u32];"
+	"if r0 > 1 goto +0;"
+	/* r7.id == r8.id,
+	 * thus r7 precision implies r8 precision,
+	 * which implies r0 precision because of the conditional below.
+	 */
+	"if r8 >= r0 goto 1f;"
+	/* break id relation between r7 and r8 */
+	"r8 += r8;"
+	/* make r7 precise */
+	"if r7 == 0 goto 1f;"
+	"r0 /= 0;"
+"1:"
+	"r0 = 42;"
+	"exit;"
+	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* Check that mark_chain_precision() for one of the conditional jump
+ * operands does not trigger equal scalars precision propagation.
+ */
+SEC("socket")
+__success __log_level(2)
+__msg("3: (25) if r1 > 0x100 goto pc+0")
+__msg("frame0: regs=r1 stack= before 2: (bf) r1 = r0")
+__naked void cjmp_no_linked_regs_trigger(void)
+{
+	asm volatile (
+	/* r0 = random number up to 0xff */
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	/* tie r0.id == r1.id */
+	"r1 = r0;"
+	/* the jump below would be predicted, thus r1 would be marked precise,
+	 * this should not imply precision mark for r0
+	 */
+	"if r1 > 256 goto +0;"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
 /* Verify that check_ids() is used by regsafe() for scalars.
  *
  * r9 = ... some pointer with range X ...
diff --git a/tools/testing/selftests/bpf/progs/verifier_sdiv.c b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
index 2a2271cf0294..148d2299e5b4 100644
--- a/tools/testing/selftests/bpf/progs/verifier_sdiv.c
+++ b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <linux/bpf.h>
+#include <limits.h>
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
@@ -770,6 +771,444 @@ __naked void smod64_zero_divisor(void)
 "	::: __clobber_all);
 }
 
+SEC("socket")
+__description("SDIV64, overflow r/r, LLONG_MIN/-1")
+__success __retval(1)
+__arch_x86_64
+__xlated("0: r2 = 0x8000000000000000")
+__xlated("2: r3 = -1")
+__xlated("3: r4 = r2")
+__xlated("4: r11 = r3")
+__xlated("5: r11 += 1")
+__xlated("6: if r11 > 0x1 goto pc+4")
+__xlated("7: if r11 == 0x0 goto pc+1")
+__xlated("8: r2 = 0")
+__xlated("9: r2 = -r2")
+__xlated("10: goto pc+1")
+__xlated("11: r2 s/= r3")
+__xlated("12: r0 = 0")
+__xlated("13: if r2 != r4 goto pc+1")
+__xlated("14: r0 = 1")
+__xlated("15: exit")
+__naked void sdiv64_overflow_rr(void)
+{
+	asm volatile ("					\
+	r2 = %[llong_min] ll;				\
+	r3 = -1;					\
+	r4 = r2;					\
+	r2 s/= r3;					\
+	r0 = 0;						\
+	if r2 != r4 goto +1;				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_const(llong_min, LLONG_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, r/r, small_val/-1")
+__success __retval(-5)
+__arch_x86_64
+__xlated("0: r2 = 5")
+__xlated("1: r3 = -1")
+__xlated("2: r11 = r3")
+__xlated("3: r11 += 1")
+__xlated("4: if r11 > 0x1 goto pc+4")
+__xlated("5: if r11 == 0x0 goto pc+1")
+__xlated("6: r2 = 0")
+__xlated("7: r2 = -r2")
+__xlated("8: goto pc+1")
+__xlated("9: r2 s/= r3")
+__xlated("10: r0 = r2")
+__xlated("11: exit")
+__naked void sdiv64_rr_divisor_neg_1(void)
+{
+	asm volatile ("					\
+	r2 = 5;						\
+	r3 = -1;					\
+	r2 s/= r3;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, overflow r/i, LLONG_MIN/-1")
+__success __retval(1)
+__arch_x86_64
+__xlated("0: r2 = 0x8000000000000000")
+__xlated("2: r4 = r2")
+__xlated("3: r2 = -r2")
+__xlated("4: r0 = 0")
+__xlated("5: if r2 != r4 goto pc+1")
+__xlated("6: r0 = 1")
+__xlated("7: exit")
+__naked void sdiv64_overflow_ri(void)
+{
+	asm volatile ("					\
+	r2 = %[llong_min] ll;				\
+	r4 = r2;					\
+	r2 s/= -1;					\
+	r0 = 0;						\
+	if r2 != r4 goto +1;				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_const(llong_min, LLONG_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, r/i, small_val/-1")
+__success __retval(-5)
+__arch_x86_64
+__xlated("0: r2 = 5")
+__xlated("1: r4 = r2")
+__xlated("2: r2 = -r2")
+__xlated("3: r0 = r2")
+__xlated("4: exit")
+__naked void sdiv64_ri_divisor_neg_1(void)
+{
+	asm volatile ("					\
+	r2 = 5;						\
+	r4 = r2;					\
+	r2 s/= -1;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, overflow r/r, INT_MIN/-1")
+__success __retval(1)
+__arch_x86_64
+__xlated("0: w2 = -2147483648")
+__xlated("1: w3 = -1")
+__xlated("2: w4 = w2")
+__xlated("3: r11 = r3")
+__xlated("4: w11 += 1")
+__xlated("5: if w11 > 0x1 goto pc+4")
+__xlated("6: if w11 == 0x0 goto pc+1")
+__xlated("7: w2 = 0")
+__xlated("8: w2 = -w2")
+__xlated("9: goto pc+1")
+__xlated("10: w2 s/= w3")
+__xlated("11: r0 = 0")
+__xlated("12: if w2 != w4 goto pc+1")
+__xlated("13: r0 = 1")
+__xlated("14: exit")
+__naked void sdiv32_overflow_rr(void)
+{
+	asm volatile ("					\
+	w2 = %[int_min];				\
+	w3 = -1;					\
+	w4 = w2;					\
+	w2 s/= w3;					\
+	r0 = 0;						\
+	if w2 != w4 goto +1;				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, r/r, small_val/-1")
+__success __retval(5)
+__arch_x86_64
+__xlated("0: w2 = -5")
+__xlated("1: w3 = -1")
+__xlated("2: w4 = w2")
+__xlated("3: r11 = r3")
+__xlated("4: w11 += 1")
+__xlated("5: if w11 > 0x1 goto pc+4")
+__xlated("6: if w11 == 0x0 goto pc+1")
+__xlated("7: w2 = 0")
+__xlated("8: w2 = -w2")
+__xlated("9: goto pc+1")
+__xlated("10: w2 s/= w3")
+__xlated("11: w0 = w2")
+__xlated("12: exit")
+__naked void sdiv32_rr_divisor_neg_1(void)
+{
+	asm volatile ("					\
+	w2 = -5;					\
+	w3 = -1;					\
+	w4 = w2;					\
+	w2 s/= w3;					\
+	w0 = w2;					\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, overflow r/i, INT_MIN/-1")
+__success __retval(1)
+__arch_x86_64
+__xlated("0: w2 = -2147483648")
+__xlated("1: w4 = w2")
+__xlated("2: w2 = -w2")
+__xlated("3: r0 = 0")
+__xlated("4: if w2 != w4 goto pc+1")
+__xlated("5: r0 = 1")
+__xlated("6: exit")
+__naked void sdiv32_overflow_ri(void)
+{
+	asm volatile ("					\
+	w2 = %[int_min];				\
+	w4 = w2;					\
+	w2 s/= -1;					\
+	r0 = 0;						\
+	if w2 != w4 goto +1;				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, r/i, small_val/-1")
+__success __retval(-5)
+__arch_x86_64
+__xlated("0: w2 = 5")
+__xlated("1: w4 = w2")
+__xlated("2: w2 = -w2")
+__xlated("3: w0 = w2")
+__xlated("4: exit")
+__naked void sdiv32_ri_divisor_neg_1(void)
+{
+	asm volatile ("					\
+	w2 = 5;						\
+	w4 = w2;					\
+	w2 s/= -1;					\
+	w0 = w2;					\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, overflow r/r, LLONG_MIN/-1")
+__success __retval(0)
+__arch_x86_64
+__xlated("0: r2 = 0x8000000000000000")
+__xlated("2: r3 = -1")
+__xlated("3: r4 = r2")
+__xlated("4: r11 = r3")
+__xlated("5: r11 += 1")
+__xlated("6: if r11 > 0x1 goto pc+3")
+__xlated("7: if r11 == 0x1 goto pc+3")
+__xlated("8: w2 = 0")
+__xlated("9: goto pc+1")
+__xlated("10: r2 s%= r3")
+__xlated("11: r0 = r2")
+__xlated("12: exit")
+__naked void smod64_overflow_rr(void)
+{
+	asm volatile ("					\
+	r2 = %[llong_min] ll;				\
+	r3 = -1;					\
+	r4 = r2;					\
+	r2 s%%= r3;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	: __imm_const(llong_min, LLONG_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, r/r, small_val/-1")
+__success __retval(0)
+__arch_x86_64
+__xlated("0: r2 = 5")
+__xlated("1: r3 = -1")
+__xlated("2: r4 = r2")
+__xlated("3: r11 = r3")
+__xlated("4: r11 += 1")
+__xlated("5: if r11 > 0x1 goto pc+3")
+__xlated("6: if r11 == 0x1 goto pc+3")
+__xlated("7: w2 = 0")
+__xlated("8: goto pc+1")
+__xlated("9: r2 s%= r3")
+__xlated("10: r0 = r2")
+__xlated("11: exit")
+__naked void smod64_rr_divisor_neg_1(void)
+{
+	asm volatile ("					\
+	r2 = 5;						\
+	r3 = -1;					\
+	r4 = r2;					\
+	r2 s%%= r3;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, overflow r/i, LLONG_MIN/-1")
+__success __retval(0)
+__arch_x86_64
+__xlated("0: r2 = 0x8000000000000000")
+__xlated("2: r4 = r2")
+__xlated("3: w2 = 0")
+__xlated("4: r0 = r2")
+__xlated("5: exit")
+__naked void smod64_overflow_ri(void)
+{
+	asm volatile ("					\
+	r2 = %[llong_min] ll;				\
+	r4 = r2;					\
+	r2 s%%= -1;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	: __imm_const(llong_min, LLONG_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, r/i, small_val/-1")
+__success __retval(0)
+__arch_x86_64
+__xlated("0: r2 = 5")
+__xlated("1: r4 = r2")
+__xlated("2: w2 = 0")
+__xlated("3: r0 = r2")
+__xlated("4: exit")
+__naked void smod64_ri_divisor_neg_1(void)
+{
+	asm volatile ("					\
+	r2 = 5;						\
+	r4 = r2;					\
+	r2 s%%= -1;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, overflow r/r, INT_MIN/-1")
+__success __retval(0)
+__arch_x86_64
+__xlated("0: w2 = -2147483648")
+__xlated("1: w3 = -1")
+__xlated("2: w4 = w2")
+__xlated("3: r11 = r3")
+__xlated("4: w11 += 1")
+__xlated("5: if w11 > 0x1 goto pc+3")
+__xlated("6: if w11 == 0x1 goto pc+4")
+__xlated("7: w2 = 0")
+__xlated("8: goto pc+1")
+__xlated("9: w2 s%= w3")
+__xlated("10: goto pc+1")
+__xlated("11: w2 = w2")
+__xlated("12: r0 = r2")
+__xlated("13: exit")
+__naked void smod32_overflow_rr(void)
+{
+	asm volatile ("					\
+	w2 = %[int_min];				\
+	w3 = -1;					\
+	w4 = w2;					\
+	w2 s%%= w3;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, r/r, small_val/-1")
+__success __retval(0)
+__arch_x86_64
+__xlated("0: w2 = -5")
+__xlated("1: w3 = -1")
+__xlated("2: w4 = w2")
+__xlated("3: r11 = r3")
+__xlated("4: w11 += 1")
+__xlated("5: if w11 > 0x1 goto pc+3")
+__xlated("6: if w11 == 0x1 goto pc+4")
+__xlated("7: w2 = 0")
+__xlated("8: goto pc+1")
+__xlated("9: w2 s%= w3")
+__xlated("10: goto pc+1")
+__xlated("11: w2 = w2")
+__xlated("12: r0 = r2")
+__xlated("13: exit")
+__naked void smod32_rr_divisor_neg_1(void)
+{
+	asm volatile ("					\
+	w2 = -5;				\
+	w3 = -1;					\
+	w4 = w2;					\
+	w2 s%%= w3;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, overflow r/i, INT_MIN/-1")
+__success __retval(0)
+__arch_x86_64
+__xlated("0: w2 = -2147483648")
+__xlated("1: w4 = w2")
+__xlated("2: w2 = 0")
+__xlated("3: r0 = r2")
+__xlated("4: exit")
+__naked void smod32_overflow_ri(void)
+{
+	asm volatile ("					\
+	w2 = %[int_min];				\
+	w4 = w2;					\
+	w2 s%%= -1;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, r/i, small_val/-1")
+__success __retval(0)
+__arch_x86_64
+__xlated("0: w2 = 5")
+__xlated("1: w4 = w2")
+__xlated("2: w2 = 0")
+__xlated("3: w0 = w2")
+__xlated("4: exit")
+__naked void smod32_ri_divisor_neg_1(void)
+{
+	asm volatile ("					\
+	w2 = 5;						\
+	w4 = w2;					\
+	w2 s%%= -1;					\
+	w0 = w2;					\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
 #else
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
index 85e48069c9e6..671d9f415dbf 100644
--- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
+++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
@@ -402,7 +402,7 @@ __naked void spill_32bit_of_64bit_fail(void)
 	*(u32*)(r10 - 8) = r1;				\
 	/* 32-bit fill r2 from stack. */		\
 	r2 = *(u32*)(r10 - 8);				\
-	/* Compare r2 with another register to trigger find_equal_scalars.\
+	/* Compare r2 with another register to trigger sync_linked_regs.\
 	 * Having one random bit is important here, otherwise the verifier cuts\
 	 * the corners. If the ID was mistakenly preserved on spill, this would\
 	 * cause the verifier to think that r1 is also equal to zero in one of\
@@ -441,7 +441,7 @@ __naked void spill_16bit_of_32bit_fail(void)
 	*(u16*)(r10 - 8) = r1;				\
 	/* 16-bit fill r2 from stack. */		\
 	r2 = *(u16*)(r10 - 8);				\
-	/* Compare r2 with another register to trigger find_equal_scalars.\
+	/* Compare r2 with another register to trigger sync_linked_regs.\
 	 * Having one random bit is important here, otherwise the verifier cuts\
 	 * the corners. If the ID was mistakenly preserved on spill, this would\
 	 * cause the verifier to think that r1 is also equal to zero in one of\
@@ -833,7 +833,7 @@ __naked void spill_64bit_of_64bit_ok(void)
 	*(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.\
+	/* Compare r1 with another register to trigger sync_linked_regs.\
 	 * Having one random bit is important here, otherwise the verifier cuts\
 	 * the corners.					\
 	 */						\
@@ -866,7 +866,7 @@ __naked void spill_32bit_of_32bit_ok(void)
 	*(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.\
+	/* Compare r1 with another register to trigger sync_linked_regs.\
 	 * Having one random bit is important here, otherwise the verifier cuts\
 	 * the corners.					\
 	 */						\
@@ -899,7 +899,7 @@ __naked void spill_16bit_of_16bit_ok(void)
 	*(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.\
+	/* Compare r1 with another register to trigger sync_linked_regs.\
 	 * Having one random bit is important here, otherwise the verifier cuts\
 	 * the corners.					\
 	 */						\
@@ -932,7 +932,7 @@ __naked void spill_8bit_of_8bit_ok(void)
 	*(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.\
+	/* Compare r1 with another register to trigger sync_linked_regs.\
 	 * Having one random bit is important here, otherwise the verifier cuts\
 	 * the corners.					\
 	 */						\
@@ -1029,7 +1029,7 @@ __naked void fill_32bit_after_spill_64bit_preserve_id(void)
 	"r1 = *(u32*)(r10 - 4);"
 #endif
 	"						\
-	/* Compare r1 with another register to trigger find_equal_scalars. */\
+	/* Compare r1 with another register to trigger sync_linked_regs. */\
 	r2 = 0;						\
 	if r1 != r2 goto l0_%=;				\
 	/* The result of this comparison is predefined. */\
@@ -1070,7 +1070,7 @@ __naked void fill_32bit_after_spill_64bit_clear_id(void)
 	"r2 = *(u32*)(r10 - 4);"
 #endif
 	"						\
-	/* Compare r2 with another register to trigger find_equal_scalars.\
+	/* Compare r2 with another register to trigger sync_linked_regs.\
 	 * 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\
@@ -1213,10 +1213,10 @@ __success  __log_level(2)
  * - 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("8: (79) r1 = *(u64 *)(r10 -8)")
+__msg("9: (95) exit")
+__msg("from 2 to 7")
+__msg("8: safe")
 __msg("processed 11 insns")
 __flag(BPF_F_TEST_STATE_FREQ)
 __naked void old_stack_misc_vs_cur_ctx_ptr(void)
diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
index 6a6fad625f7e..9d415f7ce599 100644
--- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
@@ -278,7 +278,7 @@ __msg("mark_precise: frame0: last_idx 14 first_idx 9")
 __msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7")
 __msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4")
 __msg("mark_precise: frame0: regs=r6 stack= before 11: (25) if r6 > 0x3 goto pc+4")
-__msg("mark_precise: frame0: regs=r6 stack= before 10: (bf) r6 = r0")
+__msg("mark_precise: frame0: regs=r0,r6 stack= before 10: (bf) r6 = r0")
 __msg("mark_precise: frame0: regs=r0 stack= before 9: (85) call bpf_loop")
 /* State entering callback body popped from states stack */
 __msg("from 9 to 17: frame1:")
diff --git a/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c b/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c
new file mode 100644
index 000000000000..8d60c634a114
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+int main(void);
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__array(values, void (void));
+} jmp_table SEC(".maps") = {
+	.values = {
+		[0] = (void *) &main,
+	},
+};
+
+__noinline __auxiliary
+static __naked int sub(void)
+{
+	asm volatile (
+	"r2 = %[jmp_table] ll;"
+	"r3 = 0;"
+	"call 12;"
+	"exit;"
+	:
+	: __imm_addr(jmp_table)
+	: __clobber_all);
+}
+
+__success
+__arch_x86_64
+/* program entry for main(), regular function prologue */
+__jited("	endbr64")
+__jited("	nopl	(%rax,%rax)")
+__jited("	xorq	%rax, %rax")
+__jited("	pushq	%rbp")
+__jited("	movq	%rsp, %rbp")
+/* tail call prologue for program:
+ * - establish memory location for tail call counter at &rbp[-8];
+ * - spill tail_call_cnt_ptr at &rbp[-16];
+ * - expect tail call counter to be passed in rax;
+ * - for entry program rax is a raw counter, value < 33;
+ * - for tail called program rax is tail_call_cnt_ptr (value > 33).
+ */
+__jited("	endbr64")
+__jited("	cmpq	$0x21, %rax")
+__jited("	ja	L0")
+__jited("	pushq	%rax")
+__jited("	movq	%rsp, %rax")
+__jited("	jmp	L1")
+__jited("L0:	pushq	%rax")			/* rbp[-8]  = rax         */
+__jited("L1:	pushq	%rax")			/* rbp[-16] = rax         */
+/* on subprogram call restore rax to be tail_call_cnt_ptr from rbp[-16]
+ * (cause original rax might be clobbered by this point)
+ */
+__jited("	movq	-0x10(%rbp), %rax")
+__jited("	callq	0x{{.*}}")		/* call to sub()          */
+__jited("	xorl	%eax, %eax")
+__jited("	leave")
+__jited("	{{(retq|jmp	0x)}}")		/* return or jump to rethunk */
+__jited("...")
+/* subprogram entry for sub(), regular function prologue */
+__jited("	endbr64")
+__jited("	nopl	(%rax,%rax)")
+__jited("	nopl	(%rax)")
+__jited("	pushq	%rbp")
+__jited("	movq	%rsp, %rbp")
+/* tail call prologue for subprogram address of tail call counter
+ * stored at rbp[-16].
+ */
+__jited("	endbr64")
+__jited("	pushq	%rax")			/* rbp[-8]  = rax          */
+__jited("	pushq	%rax")			/* rbp[-16] = rax          */
+__jited("	movabsq	${{.*}}, %rsi")		/* r2 = &jmp_table         */
+__jited("	xorl	%edx, %edx")		/* r3 = 0                  */
+/* bpf_tail_call implementation:
+ * - load tail_call_cnt_ptr from rbp[-16];
+ * - if *tail_call_cnt_ptr < 33, increment it and jump to target;
+ * - otherwise do nothing.
+ */
+__jited("	movq	-0x10(%rbp), %rax")
+__jited("	cmpq	$0x21, (%rax)")
+__jited("	jae	L0")
+__jited("	nopl	(%rax,%rax)")
+__jited("	addq	$0x1, (%rax)")		/* *tail_call_cnt_ptr += 1 */
+__jited("	popq	%rax")
+__jited("	popq	%rax")
+__jited("	jmp	{{.*}}")		/* jump to tail call tgt   */
+__jited("L0:	leave")
+__jited("	{{(retq|jmp	0x)}}")		/* return or jump to rethunk */
+SEC("tc")
+__naked int main(void)
+{
+	asm volatile (
+	"call %[sub];"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm(sub)
+	: __clobber_all);
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c b/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c
new file mode 100644
index 000000000000..a7c0a553aa50
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google LLC. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+static char buf[64];
+
+SEC("lsm.s/file_open")
+__success
+int BPF_PROG(get_task_exe_file_and_put_kfunc_from_current_sleepable)
+{
+	struct file *acquired;
+
+	acquired = bpf_get_task_exe_file(bpf_get_current_task_btf());
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm/file_open")
+__success
+int BPF_PROG(get_task_exe_file_and_put_kfunc_from_current_non_sleepable, struct file *file)
+{
+	struct file *acquired;
+
+	acquired = bpf_get_task_exe_file(bpf_get_current_task_btf());
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm.s/task_alloc")
+__success
+int BPF_PROG(get_task_exe_file_and_put_kfunc_from_argument,
+	     struct task_struct *task)
+{
+	struct file *acquired;
+
+	acquired = bpf_get_task_exe_file(task);
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm.s/inode_getattr")
+__success
+int BPF_PROG(path_d_path_from_path_argument, struct path *path)
+{
+	int ret;
+
+	ret = bpf_path_d_path(path, buf, sizeof(buf));
+	__sink(ret);
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__success
+int BPF_PROG(path_d_path_from_file_argument, struct file *file)
+{
+	int ret;
+	struct path *path;
+
+	/* The f_path member is a path which is embedded directly within a
+	 * file. Therefore, a pointer to such embedded members are still
+	 * recognized by the BPF verifier as being PTR_TRUSTED as it's
+	 * essentially PTR_TRUSTED w/ a non-zero fixed offset.
+	 */
+	path = &file->f_path;
+	ret = bpf_path_d_path(path, buf, sizeof(buf));
+	__sink(ret);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c b/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c
new file mode 100644
index 000000000000..d6d3f4fcb24c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google LLC. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <linux/limits.h>
+
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+static char buf[PATH_MAX];
+
+SEC("lsm.s/file_open")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+int BPF_PROG(get_task_exe_file_kfunc_null)
+{
+	struct file *acquired;
+
+	/* Can't pass a NULL pointer to bpf_get_task_exe_file(). */
+	acquired = bpf_get_task_exe_file(NULL);
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm.s/inode_getxattr")
+__failure __msg("arg#0 pointer type STRUCT task_struct must point to scalar, or struct with scalar")
+int BPF_PROG(get_task_exe_file_kfunc_fp)
+{
+	u64 x;
+	struct file *acquired;
+	struct task_struct *task;
+
+	task = (struct task_struct *)&x;
+	/* Can't pass random frame pointer to bpf_get_task_exe_file(). */
+	acquired = bpf_get_task_exe_file(task);
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("R1 must be referenced or trusted")
+int BPF_PROG(get_task_exe_file_kfunc_untrusted)
+{
+	struct file *acquired;
+	struct task_struct *parent;
+
+	/* Walking a trusted struct task_struct returned from
+	 * bpf_get_current_task_btf() yields an untrusted pointer.
+	 */
+	parent = bpf_get_current_task_btf()->parent;
+	/* Can't pass untrusted pointer to bpf_get_task_exe_file(). */
+	acquired = bpf_get_task_exe_file(parent);
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("Unreleased reference")
+int BPF_PROG(get_task_exe_file_kfunc_unreleased)
+{
+	struct file *acquired;
+
+	acquired = bpf_get_task_exe_file(bpf_get_current_task_btf());
+	if (!acquired)
+		return 0;
+
+	/* Acquired but never released. */
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("release kernel function bpf_put_file expects")
+int BPF_PROG(put_file_kfunc_unacquired, struct file *file)
+{
+	/* Can't release an unacquired pointer. */
+	bpf_put_file(file);
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+int BPF_PROG(path_d_path_kfunc_null)
+{
+	/* Can't pass NULL value to bpf_path_d_path() kfunc. */
+	bpf_path_d_path(NULL, buf, sizeof(buf));
+	return 0;
+}
+
+SEC("lsm.s/task_alloc")
+__failure __msg("R1 must be referenced or trusted")
+int BPF_PROG(path_d_path_kfunc_untrusted_from_argument, struct task_struct *task)
+{
+	struct path *root;
+
+	/* Walking a trusted argument typically yields an untrusted
+	 * pointer. This is one example of that.
+	 */
+	root = &task->fs->root;
+	bpf_path_d_path(root, buf, sizeof(buf));
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("R1 must be referenced or trusted")
+int BPF_PROG(path_d_path_kfunc_untrusted_from_current)
+{
+	struct path *pwd;
+	struct task_struct *current;
+
+	current = bpf_get_current_task_btf();
+	/* Walking a trusted pointer returned from bpf_get_current_task_btf()
+	 * yields an untrusted pointer.
+	 */
+	pwd = &current->fs->pwd;
+	bpf_path_d_path(pwd, buf, sizeof(buf));
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("kernel function bpf_path_d_path args#0 expected pointer to STRUCT path but R1 has a pointer to STRUCT file")
+int BPF_PROG(path_d_path_kfunc_type_mismatch, struct file *file)
+{
+	bpf_path_d_path((struct path *)&file->f_task_work, buf, sizeof(buf));
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("invalid access to map value, value_size=4096 off=0 size=8192")
+int BPF_PROG(path_d_path_kfunc_invalid_buf_sz, struct file *file)
+{
+	/* bpf_path_d_path() enforces a constraint on the buffer size supplied
+	 * by the BPF LSM program via the __sz annotation. buf here is set to
+	 * PATH_MAX, so let's ensure that the BPF verifier rejects BPF_PROG_LOAD
+	 * attempts if the supplied size and the actual size of the buffer
+	 * mismatches.
+	 */
+	bpf_path_d_path(&file->f_path, buf, PATH_MAX * 2);
+	return 0;
+}
+
+SEC("fentry/vfs_open")
+__failure __msg("calling kernel function bpf_path_d_path is not allowed")
+int BPF_PROG(path_d_path_kfunc_non_lsm, struct path *path, struct file *f)
+{
+	/* Calling bpf_path_d_path() from a non-LSM BPF program isn't permitted.
+	 */
+	bpf_path_d_path(path, buf, sizeof(buf));
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
index d037262c8937..682dda8dabbc 100644
--- a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
+++ b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
@@ -10,19 +10,19 @@ struct {
 	__uint(value_size, sizeof(int));
 } tx_port SEC(".maps");
 
-SEC("redirect_map_0")
+SEC("xdp")
 int xdp_redirect_map_0(struct xdp_md *xdp)
 {
 	return bpf_redirect_map(&tx_port, 0, 0);
 }
 
-SEC("redirect_map_1")
+SEC("xdp")
 int xdp_redirect_map_1(struct xdp_md *xdp)
 {
 	return bpf_redirect_map(&tx_port, 1, 0);
 }
 
-SEC("redirect_map_2")
+SEC("xdp")
 int xdp_redirect_map_2(struct xdp_md *xdp)
 {
 	return bpf_redirect_map(&tx_port, 2, 0);
diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c
deleted file mode 100644
index 0861ea60dcdd..000000000000
--- a/tools/testing/selftests/bpf/test_cgroup_storage.c
+++ /dev/null
@@ -1,174 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <assert.h>
-#include <bpf/bpf.h>
-#include <linux/filter.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <sys/sysinfo.h>
-
-#include "bpf_util.h"
-#include "cgroup_helpers.h"
-#include "testing_helpers.h"
-
-char bpf_log_buf[BPF_LOG_BUF_SIZE];
-
-#define TEST_CGROUP "/test-bpf-cgroup-storage-buf/"
-
-int main(int argc, char **argv)
-{
-	struct bpf_insn prog[] = {
-		BPF_LD_MAP_FD(BPF_REG_1, 0), /* percpu map fd */
-		BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			     BPF_FUNC_get_local_storage),
-		BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0),
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1),
-		BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0),
-
-		BPF_LD_MAP_FD(BPF_REG_1, 0), /* map fd */
-		BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			     BPF_FUNC_get_local_storage),
-		BPF_MOV64_IMM(BPF_REG_1, 1),
-		BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_0, BPF_REG_1, 0),
-		BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
-		BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x1),
-		BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-		BPF_EXIT_INSN(),
-	};
-	size_t insns_cnt = ARRAY_SIZE(prog);
-	int error = EXIT_FAILURE;
-	int map_fd, percpu_map_fd, prog_fd, cgroup_fd;
-	struct bpf_cgroup_storage_key key;
-	unsigned long long value;
-	unsigned long long *percpu_value;
-	int cpu, nproc;
-
-	nproc = bpf_num_possible_cpus();
-	percpu_value = malloc(sizeof(*percpu_value) * nproc);
-	if (!percpu_value) {
-		printf("Not enough memory for per-cpu area (%d cpus)\n", nproc);
-		goto err;
-	}
-
-	/* Use libbpf 1.0 API mode */
-	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
-
-	map_fd = bpf_map_create(BPF_MAP_TYPE_CGROUP_STORAGE, NULL, sizeof(key),
-				sizeof(value), 0, NULL);
-	if (map_fd < 0) {
-		printf("Failed to create map: %s\n", strerror(errno));
-		goto out;
-	}
-
-	percpu_map_fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, NULL,
-				       sizeof(key), sizeof(value), 0, NULL);
-	if (percpu_map_fd < 0) {
-		printf("Failed to create map: %s\n", strerror(errno));
-		goto out;
-	}
-
-	prog[0].imm = percpu_map_fd;
-	prog[7].imm = map_fd;
-	prog_fd = bpf_test_load_program(BPF_PROG_TYPE_CGROUP_SKB,
-				   prog, insns_cnt, "GPL", 0,
-				   bpf_log_buf, BPF_LOG_BUF_SIZE);
-	if (prog_fd < 0) {
-		printf("Failed to load bpf program: %s\n", bpf_log_buf);
-		goto out;
-	}
-
-	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
-
-	/* Attach the bpf program */
-	if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0)) {
-		printf("Failed to attach bpf program\n");
-		goto err;
-	}
-
-	if (bpf_map_get_next_key(map_fd, NULL, &key)) {
-		printf("Failed to get the first key in cgroup storage\n");
-		goto err;
-	}
-
-	if (bpf_map_lookup_elem(map_fd, &key, &value)) {
-		printf("Failed to lookup cgroup storage 0\n");
-		goto err;
-	}
-
-	for (cpu = 0; cpu < nproc; cpu++)
-		percpu_value[cpu] = 1000;
-
-	if (bpf_map_update_elem(percpu_map_fd, &key, percpu_value, 0)) {
-		printf("Failed to update the data in the cgroup storage\n");
-		goto err;
-	}
-
-	/* Every second packet should be dropped */
-	assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
-	assert(system("ping localhost -c 1 -W 1 -q > /dev/null"));
-	assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
-
-	/* Check the counter in the cgroup local storage */
-	if (bpf_map_lookup_elem(map_fd, &key, &value)) {
-		printf("Failed to lookup cgroup storage\n");
-		goto err;
-	}
-
-	if (value != 3) {
-		printf("Unexpected data in the cgroup storage: %llu\n", value);
-		goto err;
-	}
-
-	/* Bump the counter in the cgroup local storage */
-	value++;
-	if (bpf_map_update_elem(map_fd, &key, &value, 0)) {
-		printf("Failed to update the data in the cgroup storage\n");
-		goto err;
-	}
-
-	/* Every second packet should be dropped */
-	assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
-	assert(system("ping localhost -c 1 -W 1 -q > /dev/null"));
-	assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
-
-	/* Check the final value of the counter in the cgroup local storage */
-	if (bpf_map_lookup_elem(map_fd, &key, &value)) {
-		printf("Failed to lookup the cgroup storage\n");
-		goto err;
-	}
-
-	if (value != 7) {
-		printf("Unexpected data in the cgroup storage: %llu\n", value);
-		goto err;
-	}
-
-	/* Check the final value of the counter in the percpu local storage */
-
-	for (cpu = 0; cpu < nproc; cpu++)
-		percpu_value[cpu] = 0;
-
-	if (bpf_map_lookup_elem(percpu_map_fd, &key, percpu_value)) {
-		printf("Failed to lookup the per-cpu cgroup storage\n");
-		goto err;
-	}
-
-	value = 0;
-	for (cpu = 0; cpu < nproc; cpu++)
-		value += percpu_value[cpu];
-
-	if (value != nproc * 1000 + 6) {
-		printf("Unexpected data in the per-cpu cgroup storage\n");
-		goto err;
-	}
-
-	error = 0;
-	printf("test_cgroup_storage:PASS\n");
-
-err:
-	cleanup_cgroup_environment();
-	free(percpu_value);
-
-out:
-	return error;
-}
diff --git a/tools/testing/selftests/bpf/test_cpp.cpp b/tools/testing/selftests/bpf/test_cpp.cpp
index dde0bb16e782..abc2a56ab261 100644
--- a/tools/testing/selftests/bpf/test_cpp.cpp
+++ b/tools/testing/selftests/bpf/test_cpp.cpp
@@ -6,6 +6,10 @@
 #include <bpf/libbpf.h>
 #include <bpf/bpf.h>
 #include <bpf/btf.h>
+
+#ifndef _Bool
+#define _Bool bool
+#endif
 #include "test_core_extern.skel.h"
 #include "struct_ops_module.skel.h"
 
diff --git a/tools/testing/selftests/bpf/test_dev_cgroup.c b/tools/testing/selftests/bpf/test_dev_cgroup.c
deleted file mode 100644
index adeaf63cb6fa..000000000000
--- a/tools/testing/selftests/bpf/test_dev_cgroup.c
+++ /dev/null
@@ -1,85 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/* Copyright (c) 2017 Facebook
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <errno.h>
-#include <assert.h>
-#include <sys/time.h>
-
-#include <linux/bpf.h>
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include "cgroup_helpers.h"
-#include "testing_helpers.h"
-
-#define DEV_CGROUP_PROG "./dev_cgroup.bpf.o"
-
-#define TEST_CGROUP "/test-bpf-based-device-cgroup/"
-
-int main(int argc, char **argv)
-{
-	struct bpf_object *obj;
-	int error = EXIT_FAILURE;
-	int prog_fd, cgroup_fd;
-	__u32 prog_cnt;
-
-	/* Use libbpf 1.0 API mode */
-	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
-
-	if (bpf_prog_test_load(DEV_CGROUP_PROG, BPF_PROG_TYPE_CGROUP_DEVICE,
-			  &obj, &prog_fd)) {
-		printf("Failed to load DEV_CGROUP program\n");
-		goto out;
-	}
-
-	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
-	if (cgroup_fd < 0) {
-		printf("Failed to create test cgroup\n");
-		goto out;
-	}
-
-	/* Attach bpf program */
-	if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_DEVICE, 0)) {
-		printf("Failed to attach DEV_CGROUP program");
-		goto err;
-	}
-
-	if (bpf_prog_query(cgroup_fd, BPF_CGROUP_DEVICE, 0, NULL, NULL,
-			   &prog_cnt)) {
-		printf("Failed to query attached programs");
-		goto err;
-	}
-
-	/* All operations with /dev/zero and and /dev/urandom are allowed,
-	 * everything else is forbidden.
-	 */
-	assert(system("rm -f /tmp/test_dev_cgroup_null") == 0);
-	assert(system("mknod /tmp/test_dev_cgroup_null c 1 3"));
-	assert(system("rm -f /tmp/test_dev_cgroup_null") == 0);
-
-	/* /dev/zero is whitelisted */
-	assert(system("rm -f /tmp/test_dev_cgroup_zero") == 0);
-	assert(system("mknod /tmp/test_dev_cgroup_zero c 1 5") == 0);
-	assert(system("rm -f /tmp/test_dev_cgroup_zero") == 0);
-
-	assert(system("dd if=/dev/urandom of=/dev/zero count=64") == 0);
-
-	/* src is allowed, target is forbidden */
-	assert(system("dd if=/dev/urandom of=/dev/full count=64"));
-
-	/* src is forbidden, target is allowed */
-	assert(system("dd if=/dev/random of=/dev/zero count=64"));
-
-	error = 0;
-	printf("test_dev_cgroup:PASS\n");
-
-err:
-	cleanup_cgroup_environment();
-
-out:
-	return error;
-}
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index f14e10b0de96..3e9b009580d4 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -7,8 +7,10 @@
 #include <bpf/btf.h>
 
 #include "autoconf_helper.h"
+#include "disasm_helpers.h"
 #include "unpriv_helpers.h"
 #include "cap_helpers.h"
+#include "jit_disasm_helpers.h"
 
 #define str_has_pfx(str, pfx) \
 	(strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0)
@@ -18,11 +20,11 @@
 #define TEST_TAG_EXPECT_FAILURE "comment:test_expect_failure"
 #define TEST_TAG_EXPECT_SUCCESS "comment:test_expect_success"
 #define TEST_TAG_EXPECT_MSG_PFX "comment:test_expect_msg="
-#define TEST_TAG_EXPECT_REGEX_PFX "comment:test_expect_regex="
+#define TEST_TAG_EXPECT_XLATED_PFX "comment:test_expect_xlated="
 #define TEST_TAG_EXPECT_FAILURE_UNPRIV "comment:test_expect_failure_unpriv"
 #define TEST_TAG_EXPECT_SUCCESS_UNPRIV "comment:test_expect_success_unpriv"
 #define TEST_TAG_EXPECT_MSG_PFX_UNPRIV "comment:test_expect_msg_unpriv="
-#define TEST_TAG_EXPECT_REGEX_PFX_UNPRIV "comment:test_expect_regex_unpriv="
+#define TEST_TAG_EXPECT_XLATED_PFX_UNPRIV "comment:test_expect_xlated_unpriv="
 #define TEST_TAG_LOG_LEVEL_PFX "comment:test_log_level="
 #define TEST_TAG_PROG_FLAGS_PFX "comment:test_prog_flags="
 #define TEST_TAG_DESCRIPTION_PFX "comment:test_description="
@@ -31,6 +33,9 @@
 #define TEST_TAG_AUXILIARY "comment:test_auxiliary"
 #define TEST_TAG_AUXILIARY_UNPRIV "comment:test_auxiliary_unpriv"
 #define TEST_BTF_PATH "comment:test_btf_path="
+#define TEST_TAG_ARCH "comment:test_arch="
+#define TEST_TAG_JITED_PFX "comment:test_jited="
+#define TEST_TAG_JITED_PFX_UNPRIV "comment:test_jited_unpriv="
 
 /* Warning: duplicated in bpf_misc.h */
 #define POINTER_VALUE	0xcafe4all
@@ -51,15 +56,22 @@ enum mode {
 
 struct expect_msg {
 	const char *substr; /* substring match */
-	const char *regex_str; /* regex-based match */
 	regex_t regex;
+	bool is_regex;
+	bool on_next_line;
+};
+
+struct expected_msgs {
+	struct expect_msg *patterns;
+	size_t cnt;
 };
 
 struct test_subspec {
 	char *name;
 	bool expect_failure;
-	struct expect_msg *expect_msgs;
-	size_t expect_msg_cnt;
+	struct expected_msgs expect_msgs;
+	struct expected_msgs expect_xlated;
+	struct expected_msgs jited;
 	int retval;
 	bool execute;
 };
@@ -72,6 +84,7 @@ struct test_spec {
 	int log_level;
 	int prog_flags;
 	int mode_mask;
+	int arch_mask;
 	bool auxiliary;
 	bool valid;
 };
@@ -96,61 +109,152 @@ void test_loader_fini(struct test_loader *tester)
 	free(tester->log_buf);
 }
 
-static void free_test_spec(struct test_spec *spec)
+static void free_msgs(struct expected_msgs *msgs)
 {
 	int i;
 
+	for (i = 0; i < msgs->cnt; i++)
+		if (msgs->patterns[i].is_regex)
+			regfree(&msgs->patterns[i].regex);
+	free(msgs->patterns);
+	msgs->patterns = NULL;
+	msgs->cnt = 0;
+}
+
+static void free_test_spec(struct test_spec *spec)
+{
 	/* Deallocate expect_msgs arrays. */
-	for (i = 0; i < spec->priv.expect_msg_cnt; i++)
-		if (spec->priv.expect_msgs[i].regex_str)
-			regfree(&spec->priv.expect_msgs[i].regex);
-	for (i = 0; i < spec->unpriv.expect_msg_cnt; i++)
-		if (spec->unpriv.expect_msgs[i].regex_str)
-			regfree(&spec->unpriv.expect_msgs[i].regex);
+	free_msgs(&spec->priv.expect_msgs);
+	free_msgs(&spec->unpriv.expect_msgs);
+	free_msgs(&spec->priv.expect_xlated);
+	free_msgs(&spec->unpriv.expect_xlated);
+	free_msgs(&spec->priv.jited);
+	free_msgs(&spec->unpriv.jited);
 
 	free(spec->priv.name);
 	free(spec->unpriv.name);
-	free(spec->priv.expect_msgs);
-	free(spec->unpriv.expect_msgs);
-
 	spec->priv.name = NULL;
 	spec->unpriv.name = NULL;
-	spec->priv.expect_msgs = NULL;
-	spec->unpriv.expect_msgs = NULL;
 }
 
-static int push_msg(const char *substr, const char *regex_str, struct test_subspec *subspec)
+/* Compiles regular expression matching pattern.
+ * Pattern has a special syntax:
+ *
+ *   pattern := (<verbatim text> | regex)*
+ *   regex := "{{" <posix extended regular expression> "}}"
+ *
+ * In other words, pattern is a verbatim text with inclusion
+ * of regular expressions enclosed in "{{" "}}" pairs.
+ * For example, pattern "foo{{[0-9]+}}" matches strings like
+ * "foo0", "foo007", etc.
+ */
+static int compile_regex(const char *pattern, regex_t *regex)
+{
+	char err_buf[256], buf[256] = {}, *ptr, *buf_end;
+	const char *original_pattern = pattern;
+	bool in_regex = false;
+	int err;
+
+	buf_end = buf + sizeof(buf);
+	ptr = buf;
+	while (*pattern && ptr < buf_end - 2) {
+		if (!in_regex && str_has_pfx(pattern, "{{")) {
+			in_regex = true;
+			pattern += 2;
+			continue;
+		}
+		if (in_regex && str_has_pfx(pattern, "}}")) {
+			in_regex = false;
+			pattern += 2;
+			continue;
+		}
+		if (in_regex) {
+			*ptr++ = *pattern++;
+			continue;
+		}
+		/* list of characters that need escaping for extended posix regex */
+		if (strchr(".[]\\()*+?{}|^$", *pattern)) {
+			*ptr++ = '\\';
+			*ptr++ = *pattern++;
+			continue;
+		}
+		*ptr++ = *pattern++;
+	}
+	if (*pattern) {
+		PRINT_FAIL("Regexp too long: '%s'\n", original_pattern);
+		return -EINVAL;
+	}
+	if (in_regex) {
+		PRINT_FAIL("Regexp has open '{{' but no closing '}}': '%s'\n", original_pattern);
+		return -EINVAL;
+	}
+	err = regcomp(regex, buf, REG_EXTENDED | REG_NEWLINE);
+	if (err != 0) {
+		regerror(err, regex, err_buf, sizeof(err_buf));
+		PRINT_FAIL("Regexp compilation error in '%s': '%s'\n", buf, err_buf);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int __push_msg(const char *pattern, bool on_next_line, struct expected_msgs *msgs)
 {
-	void *tmp;
-	int regcomp_res;
-	char error_msg[100];
 	struct expect_msg *msg;
+	void *tmp;
+	int err;
 
-	tmp = realloc(subspec->expect_msgs,
-		      (1 + subspec->expect_msg_cnt) * sizeof(struct expect_msg));
+	tmp = realloc(msgs->patterns,
+		      (1 + msgs->cnt) * sizeof(struct expect_msg));
 	if (!tmp) {
 		ASSERT_FAIL("failed to realloc memory for messages\n");
 		return -ENOMEM;
 	}
-	subspec->expect_msgs = tmp;
-	msg = &subspec->expect_msgs[subspec->expect_msg_cnt];
+	msgs->patterns = tmp;
+	msg = &msgs->patterns[msgs->cnt];
+	msg->on_next_line = on_next_line;
+	msg->substr = pattern;
+	msg->is_regex = false;
+	if (strstr(pattern, "{{")) {
+		err = compile_regex(pattern, &msg->regex);
+		if (err)
+			return err;
+		msg->is_regex = true;
+	}
+	msgs->cnt += 1;
+	return 0;
+}
 
-	if (substr) {
-		msg->substr = substr;
-		msg->regex_str = NULL;
-	} else {
-		msg->regex_str = regex_str;
-		msg->substr = NULL;
-		regcomp_res = regcomp(&msg->regex, regex_str, REG_EXTENDED|REG_NEWLINE);
-		if (regcomp_res != 0) {
-			regerror(regcomp_res, &msg->regex, error_msg, sizeof(error_msg));
-			PRINT_FAIL("Regexp compilation error in '%s': '%s'\n",
-				   regex_str, error_msg);
-			return -EINVAL;
-		}
+static int clone_msgs(struct expected_msgs *from, struct expected_msgs *to)
+{
+	struct expect_msg *msg;
+	int i, err;
+
+	for (i = 0; i < from->cnt; i++) {
+		msg = &from->patterns[i];
+		err = __push_msg(msg->substr, msg->on_next_line, to);
+		if (err)
+			return err;
 	}
+	return 0;
+}
+
+static int push_msg(const char *substr, struct expected_msgs *msgs)
+{
+	return __push_msg(substr, false, msgs);
+}
 
-	subspec->expect_msg_cnt += 1;
+static int push_disasm_msg(const char *regex_str, bool *on_next_line, struct expected_msgs *msgs)
+{
+	int err;
+
+	if (strcmp(regex_str, "...") == 0) {
+		*on_next_line = false;
+		return 0;
+	}
+	err = __push_msg(regex_str, *on_next_line, msgs);
+	if (err)
+		return err;
+	*on_next_line = true;
 	return 0;
 }
 
@@ -202,6 +306,54 @@ static void update_flags(int *flags, int flag, bool clear)
 		*flags |= flag;
 }
 
+/* Matches a string of form '<pfx>[^=]=.*' and returns it's suffix.
+ * Used to parse btf_decl_tag values.
+ * Such values require unique prefix because compiler does not add
+ * same __attribute__((btf_decl_tag(...))) twice.
+ * Test suite uses two-component tags for such cases:
+ *
+ *   <pfx> __COUNTER__ '='
+ *
+ * For example, two consecutive __msg tags '__msg("foo") __msg("foo")'
+ * would be encoded as:
+ *
+ *   [18] DECL_TAG 'comment:test_expect_msg=0=foo' type_id=15 component_idx=-1
+ *   [19] DECL_TAG 'comment:test_expect_msg=1=foo' type_id=15 component_idx=-1
+ *
+ * And the purpose of this function is to extract 'foo' from the above.
+ */
+static const char *skip_dynamic_pfx(const char *s, const char *pfx)
+{
+	const char *msg;
+
+	if (strncmp(s, pfx, strlen(pfx)) != 0)
+		return NULL;
+	msg = s + strlen(pfx);
+	msg = strchr(msg, '=');
+	if (!msg)
+		return NULL;
+	return msg + 1;
+}
+
+enum arch {
+	ARCH_UNKNOWN	= 0x1,
+	ARCH_X86_64	= 0x2,
+	ARCH_ARM64	= 0x4,
+	ARCH_RISCV64	= 0x8,
+};
+
+static int get_current_arch(void)
+{
+#if defined(__x86_64__)
+	return ARCH_X86_64;
+#elif defined(__aarch64__)
+	return ARCH_ARM64;
+#elif defined(__riscv) && __riscv_xlen == 64
+	return ARCH_RISCV64;
+#endif
+	return ARCH_UNKNOWN;
+}
+
 /* Uses btf_decl_tag attributes to describe the expected test
  * behavior, see bpf_misc.h for detailed description of each attribute
  * and attribute combinations.
@@ -214,8 +366,15 @@ static int parse_test_spec(struct test_loader *tester,
 	const char *description = NULL;
 	bool has_unpriv_result = false;
 	bool has_unpriv_retval = false;
+	bool unpriv_xlated_on_next_line = true;
+	bool xlated_on_next_line = true;
+	bool unpriv_jit_on_next_line;
+	bool jit_on_next_line;
+	bool collect_jit = false;
 	int func_id, i, err = 0;
+	u32 arch_mask = 0;
 	struct btf *btf;
+	enum arch arch;
 
 	memset(spec, 0, sizeof(*spec));
 
@@ -270,27 +429,49 @@ static int parse_test_spec(struct test_loader *tester,
 		} else if (strcmp(s, TEST_TAG_AUXILIARY_UNPRIV) == 0) {
 			spec->auxiliary = true;
 			spec->mode_mask |= UNPRIV;
-		} else if (str_has_pfx(s, TEST_TAG_EXPECT_MSG_PFX)) {
-			msg = s + sizeof(TEST_TAG_EXPECT_MSG_PFX) - 1;
-			err = push_msg(msg, NULL, &spec->priv);
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_MSG_PFX))) {
+			err = push_msg(msg, &spec->priv.expect_msgs);
 			if (err)
 				goto cleanup;
 			spec->mode_mask |= PRIV;
-		} else if (str_has_pfx(s, TEST_TAG_EXPECT_MSG_PFX_UNPRIV)) {
-			msg = s + sizeof(TEST_TAG_EXPECT_MSG_PFX_UNPRIV) - 1;
-			err = push_msg(msg, NULL, &spec->unpriv);
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_MSG_PFX_UNPRIV))) {
+			err = push_msg(msg, &spec->unpriv.expect_msgs);
 			if (err)
 				goto cleanup;
 			spec->mode_mask |= UNPRIV;
-		} else if (str_has_pfx(s, TEST_TAG_EXPECT_REGEX_PFX)) {
-			msg = s + sizeof(TEST_TAG_EXPECT_REGEX_PFX) - 1;
-			err = push_msg(NULL, msg, &spec->priv);
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_JITED_PFX))) {
+			if (arch_mask == 0) {
+				PRINT_FAIL("__jited used before __arch_*");
+				goto cleanup;
+			}
+			if (collect_jit) {
+				err = push_disasm_msg(msg, &jit_on_next_line,
+						      &spec->priv.jited);
+				if (err)
+					goto cleanup;
+				spec->mode_mask |= PRIV;
+			}
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_JITED_PFX_UNPRIV))) {
+			if (arch_mask == 0) {
+				PRINT_FAIL("__unpriv_jited used before __arch_*");
+				goto cleanup;
+			}
+			if (collect_jit) {
+				err = push_disasm_msg(msg, &unpriv_jit_on_next_line,
+						      &spec->unpriv.jited);
+				if (err)
+					goto cleanup;
+				spec->mode_mask |= UNPRIV;
+			}
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_XLATED_PFX))) {
+			err = push_disasm_msg(msg, &xlated_on_next_line,
+					      &spec->priv.expect_xlated);
 			if (err)
 				goto cleanup;
 			spec->mode_mask |= PRIV;
-		} else if (str_has_pfx(s, TEST_TAG_EXPECT_REGEX_PFX_UNPRIV)) {
-			msg = s + sizeof(TEST_TAG_EXPECT_REGEX_PFX_UNPRIV) - 1;
-			err = push_msg(NULL, msg, &spec->unpriv);
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_XLATED_PFX_UNPRIV))) {
+			err = push_disasm_msg(msg, &unpriv_xlated_on_next_line,
+					      &spec->unpriv.expect_xlated);
 			if (err)
 				goto cleanup;
 			spec->mode_mask |= UNPRIV;
@@ -341,11 +522,30 @@ static int parse_test_spec(struct test_loader *tester,
 					goto cleanup;
 				update_flags(&spec->prog_flags, flags, clear);
 			}
+		} else if (str_has_pfx(s, TEST_TAG_ARCH)) {
+			val = s + sizeof(TEST_TAG_ARCH) - 1;
+			if (strcmp(val, "X86_64") == 0) {
+				arch = ARCH_X86_64;
+			} else if (strcmp(val, "ARM64") == 0) {
+				arch = ARCH_ARM64;
+			} else if (strcmp(val, "RISCV64") == 0) {
+				arch = ARCH_RISCV64;
+			} else {
+				PRINT_FAIL("bad arch spec: '%s'", val);
+				err = -EINVAL;
+				goto cleanup;
+			}
+			arch_mask |= arch;
+			collect_jit = get_current_arch() == arch;
+			unpriv_jit_on_next_line = true;
+			jit_on_next_line = true;
 		} else if (str_has_pfx(s, TEST_BTF_PATH)) {
 			spec->btf_custom_path = s + sizeof(TEST_BTF_PATH) - 1;
 		}
 	}
 
+	spec->arch_mask = arch_mask ?: -1;
+
 	if (spec->mode_mask == 0)
 		spec->mode_mask = PRIV;
 
@@ -387,15 +587,12 @@ static int parse_test_spec(struct test_loader *tester,
 			spec->unpriv.execute = spec->priv.execute;
 		}
 
-		if (!spec->unpriv.expect_msgs) {
-			for (i = 0; i < spec->priv.expect_msg_cnt; i++) {
-				struct expect_msg *msg = &spec->priv.expect_msgs[i];
-
-				err = push_msg(msg->substr, msg->regex_str, &spec->unpriv);
-				if (err)
-					goto cleanup;
-			}
-		}
+		if (spec->unpriv.expect_msgs.cnt == 0)
+			clone_msgs(&spec->priv.expect_msgs, &spec->unpriv.expect_msgs);
+		if (spec->unpriv.expect_xlated.cnt == 0)
+			clone_msgs(&spec->priv.expect_xlated, &spec->unpriv.expect_xlated);
+		if (spec->unpriv.jited.cnt == 0)
+			clone_msgs(&spec->priv.jited, &spec->unpriv.jited);
 	}
 
 	spec->valid = true;
@@ -434,7 +631,6 @@ static void prepare_case(struct test_loader *tester,
 	bpf_program__set_flags(prog, prog_flags | spec->prog_flags);
 
 	tester->log_buf[0] = '\0';
-	tester->next_match_pos = 0;
 }
 
 static void emit_verifier_log(const char *log_buf, bool force)
@@ -444,46 +640,84 @@ static void emit_verifier_log(const char *log_buf, bool force)
 	fprintf(stdout, "VERIFIER LOG:\n=============\n%s=============\n", log_buf);
 }
 
-static void validate_case(struct test_loader *tester,
-			  struct test_subspec *subspec,
-			  struct bpf_object *obj,
-			  struct bpf_program *prog,
-			  int load_err)
+static void emit_xlated(const char *xlated, bool force)
 {
-	int i, j, err;
-	char *match;
+	if (!force && env.verbosity == VERBOSE_NONE)
+		return;
+	fprintf(stdout, "XLATED:\n=============\n%s=============\n", xlated);
+}
+
+static void emit_jited(const char *jited, bool force)
+{
+	if (!force && env.verbosity == VERBOSE_NONE)
+		return;
+	fprintf(stdout, "JITED:\n=============\n%s=============\n", jited);
+}
+
+static void validate_msgs(char *log_buf, struct expected_msgs *msgs,
+			  void (*emit_fn)(const char *buf, bool force))
+{
+	const char *log = log_buf, *prev_match;
 	regmatch_t reg_match[1];
+	int prev_match_line;
+	int match_line;
+	int i, j, err;
 
-	for (i = 0; i < subspec->expect_msg_cnt; i++) {
-		struct expect_msg *msg = &subspec->expect_msgs[i];
+	prev_match_line = -1;
+	match_line = 0;
+	prev_match = log;
+	for (i = 0; i < msgs->cnt; i++) {
+		struct expect_msg *msg = &msgs->patterns[i];
+		const char *match = NULL, *pat_status;
+		bool wrong_line = false;
 
-		if (msg->substr) {
-			match = strstr(tester->log_buf + tester->next_match_pos, msg->substr);
+		if (!msg->is_regex) {
+			match = strstr(log, msg->substr);
 			if (match)
-				tester->next_match_pos = match - tester->log_buf + strlen(msg->substr);
+				log = match + strlen(msg->substr);
 		} else {
-			err = regexec(&msg->regex,
-				      tester->log_buf + tester->next_match_pos, 1, reg_match, 0);
+			err = regexec(&msg->regex, log, 1, reg_match, 0);
 			if (err == 0) {
-				match = tester->log_buf + tester->next_match_pos + reg_match[0].rm_so;
-				tester->next_match_pos += reg_match[0].rm_eo;
-			} else {
-				match = NULL;
+				match = log + reg_match[0].rm_so;
+				log += reg_match[0].rm_eo;
 			}
 		}
 
-		if (!ASSERT_OK_PTR(match, "expect_msg")) {
+		if (match) {
+			for (; prev_match < match; ++prev_match)
+				if (*prev_match == '\n')
+					++match_line;
+			wrong_line = msg->on_next_line && prev_match_line >= 0 &&
+				     prev_match_line + 1 != match_line;
+		}
+
+		if (!match || wrong_line) {
+			PRINT_FAIL("expect_msg\n");
 			if (env.verbosity == VERBOSE_NONE)
-				emit_verifier_log(tester->log_buf, true /*force*/);
+				emit_fn(log_buf, true /*force*/);
 			for (j = 0; j <= i; j++) {
-				msg = &subspec->expect_msgs[j];
+				msg = &msgs->patterns[j];
+				if (j < i)
+					pat_status = "MATCHED   ";
+				else if (wrong_line)
+					pat_status = "WRONG LINE";
+				else
+					pat_status = "EXPECTED  ";
+				msg = &msgs->patterns[j];
 				fprintf(stderr, "%s %s: '%s'\n",
-					j < i ? "MATCHED " : "EXPECTED",
-					msg->substr ? "SUBSTR" : " REGEX",
-					msg->substr ?: msg->regex_str);
+					pat_status,
+					msg->is_regex ? " REGEX" : "SUBSTR",
+					msg->substr);
 			}
-			return;
+			if (wrong_line) {
+				fprintf(stderr,
+					"expecting match at line %d, actual match is at line %d\n",
+					prev_match_line + 1, match_line);
+			}
+			break;
 		}
+
+		prev_match_line = match_line;
 	}
 }
 
@@ -611,6 +845,37 @@ static bool should_do_test_run(struct test_spec *spec, struct test_subspec *subs
 	return true;
 }
 
+/* Get a disassembly of BPF program after verifier applies all rewrites */
+static int get_xlated_program_text(int prog_fd, char *text, size_t text_sz)
+{
+	struct bpf_insn *insn_start = NULL, *insn, *insn_end;
+	__u32 insns_cnt = 0, i;
+	char buf[64];
+	FILE *out = NULL;
+	int err;
+
+	err = get_xlated_program(prog_fd, &insn_start, &insns_cnt);
+	if (!ASSERT_OK(err, "get_xlated_program"))
+		goto out;
+	out = fmemopen(text, text_sz, "w");
+	if (!ASSERT_OK_PTR(out, "open_memstream"))
+		goto out;
+	insn_end = insn_start + insns_cnt;
+	insn = insn_start;
+	while (insn < insn_end) {
+		i = insn - insn_start;
+		insn = disasm_insn(insn, buf, sizeof(buf));
+		fprintf(out, "%d: %s\n", i, buf);
+	}
+	fflush(out);
+
+out:
+	free(insn_start);
+	if (out)
+		fclose(out);
+	return err;
+}
+
 /* this function is forced noinline and has short generic name to look better
  * in test_progs output (in case of a failure)
  */
@@ -625,16 +890,23 @@ void run_subtest(struct test_loader *tester,
 {
 	struct test_subspec *subspec = unpriv ? &spec->unpriv : &spec->priv;
 	struct bpf_program *tprog = NULL, *tprog_iter;
+	struct bpf_link *link, *links[32] = {};
 	struct test_spec *spec_iter;
 	struct cap_state caps = {};
 	struct bpf_object *tobj;
 	struct bpf_map *map;
 	int retval, err, i;
+	int links_cnt = 0;
 	bool should_load;
 
 	if (!test__start_subtest(subspec->name))
 		return;
 
+	if ((get_current_arch() & spec->arch_mask) == 0) {
+		test__skip();
+		return;
+	}
+
 	if (unpriv) {
 		if (!can_execute_unpriv(tester, spec)) {
 			test__skip();
@@ -695,9 +967,32 @@ void run_subtest(struct test_loader *tester,
 			goto tobj_cleanup;
 		}
 	}
-
 	emit_verifier_log(tester->log_buf, false /*force*/);
-	validate_case(tester, subspec, tobj, tprog, err);
+	validate_msgs(tester->log_buf, &subspec->expect_msgs, emit_verifier_log);
+
+	if (subspec->expect_xlated.cnt) {
+		err = get_xlated_program_text(bpf_program__fd(tprog),
+					      tester->log_buf, tester->log_buf_sz);
+		if (err)
+			goto tobj_cleanup;
+		emit_xlated(tester->log_buf, false /*force*/);
+		validate_msgs(tester->log_buf, &subspec->expect_xlated, emit_xlated);
+	}
+
+	if (subspec->jited.cnt) {
+		err = get_jited_program_text(bpf_program__fd(tprog),
+					     tester->log_buf, tester->log_buf_sz);
+		if (err == -EOPNOTSUPP) {
+			printf("%s:SKIP: jited programs disassembly is not supported,\n", __func__);
+			printf("%s:SKIP: tests are built w/o LLVM development libs\n", __func__);
+			test__skip();
+			goto tobj_cleanup;
+		}
+		if (!ASSERT_EQ(err, 0, "get_jited_program_text"))
+			goto tobj_cleanup;
+		emit_jited(tester->log_buf, false /*force*/);
+		validate_msgs(tester->log_buf, &subspec->jited, emit_jited);
+	}
 
 	if (should_do_test_run(spec, subspec)) {
 		/* For some reason test_verifier executes programs
@@ -706,6 +1001,26 @@ void run_subtest(struct test_loader *tester,
 		if (restore_capabilities(&caps))
 			goto tobj_cleanup;
 
+		/* Do bpf_map__attach_struct_ops() for each struct_ops map.
+		 * This should trigger bpf_struct_ops->reg callback on kernel side.
+		 */
+		bpf_object__for_each_map(map, tobj) {
+			if (!bpf_map__autocreate(map) ||
+			    bpf_map__type(map) != BPF_MAP_TYPE_STRUCT_OPS)
+				continue;
+			if (links_cnt >= ARRAY_SIZE(links)) {
+				PRINT_FAIL("too many struct_ops maps");
+				goto tobj_cleanup;
+			}
+			link = bpf_map__attach_struct_ops(map);
+			if (!link) {
+				PRINT_FAIL("bpf_map__attach_struct_ops failed for map %s: err=%d\n",
+					   bpf_map__name(map), err);
+				goto tobj_cleanup;
+			}
+			links[links_cnt++] = link;
+		}
+
 		if (tester->pre_execution_cb) {
 			err = tester->pre_execution_cb(tobj);
 			if (err) {
@@ -720,9 +1035,14 @@ void run_subtest(struct test_loader *tester,
 			PRINT_FAIL("Unexpected retval: %d != %d\n", retval, subspec->retval);
 			goto tobj_cleanup;
 		}
+		/* redo bpf_map__attach_struct_ops for each test */
+		while (links_cnt > 0)
+			bpf_link__destroy(links[--links_cnt]);
 	}
 
 tobj_cleanup:
+	while (links_cnt > 0)
+		bpf_link__destroy(links[--links_cnt]);
 	bpf_object__close(tobj);
 subtest_cleanup:
 	test__end_subtest();
diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c
index 4d0650cfb5cd..fda7589c5023 100644
--- a/tools/testing/selftests/bpf/test_lru_map.c
+++ b/tools/testing/selftests/bpf/test_lru_map.c
@@ -126,7 +126,8 @@ static int sched_next_online(int pid, int *next_to_try)
 
 	while (next < nr_cpus) {
 		CPU_ZERO(&cpuset);
-		CPU_SET(next++, &cpuset);
+		CPU_SET(next, &cpuset);
+		next++;
 		if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset)) {
 			ret = 0;
 			break;
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index dfbab214f4d1..905d5981ace1 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1515,7 +1515,7 @@ again:
 		       value == key);
 	}
 
-	/* Now let's delete all elemenets in parallel. */
+	/* Now let's delete all elements in parallel. */
 	data[1] = DO_DELETE;
 	run_parallel(TASKS, test_update_delete, data);
 
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 89ff704e9dad..c7a70e1a1085 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -10,7 +10,6 @@
 #include <sched.h>
 #include <signal.h>
 #include <string.h>
-#include <execinfo.h> /* backtrace */
 #include <sys/sysinfo.h> /* get_nprocs */
 #include <netinet/in.h>
 #include <sys/select.h>
@@ -19,6 +18,25 @@
 #include <bpf/btf.h>
 #include "json_writer.h"
 
+#include "network_helpers.h"
+
+#ifdef __GLIBC__
+#include <execinfo.h> /* backtrace */
+#endif
+
+/* Default backtrace funcs if missing at link */
+__weak int backtrace(void **buffer, int size)
+{
+	return 0;
+}
+
+__weak void backtrace_symbols_fd(void *const *buffer, int size, int fd)
+{
+	dprintf(fd, "<backtrace not supported>\n");
+}
+
+int env_verbosity = 0;
+
 static bool verbose(void)
 {
 	return env.verbosity > VERBOSE_NONE;
@@ -37,15 +55,15 @@ static void stdio_hijack_init(char **log_buf, size_t *log_cnt)
 
 	stdout = open_memstream(log_buf, log_cnt);
 	if (!stdout) {
-		stdout = env.stdout;
+		stdout = env.stdout_saved;
 		perror("open_memstream");
 		return;
 	}
 
 	if (env.subtest_state)
-		env.subtest_state->stdout = stdout;
+		env.subtest_state->stdout_saved = stdout;
 	else
-		env.test_state->stdout = stdout;
+		env.test_state->stdout_saved = stdout;
 
 	stderr = stdout;
 #endif
@@ -59,8 +77,8 @@ static void stdio_hijack(char **log_buf, size_t *log_cnt)
 		return;
 	}
 
-	env.stdout = stdout;
-	env.stderr = stderr;
+	env.stdout_saved = stdout;
+	env.stderr_saved = stderr;
 
 	stdio_hijack_init(log_buf, log_cnt);
 #endif
@@ -77,13 +95,13 @@ static void stdio_restore_cleanup(void)
 	fflush(stdout);
 
 	if (env.subtest_state) {
-		fclose(env.subtest_state->stdout);
-		env.subtest_state->stdout = NULL;
-		stdout = env.test_state->stdout;
-		stderr = env.test_state->stdout;
+		fclose(env.subtest_state->stdout_saved);
+		env.subtest_state->stdout_saved = NULL;
+		stdout = env.test_state->stdout_saved;
+		stderr = env.test_state->stdout_saved;
 	} else {
-		fclose(env.test_state->stdout);
-		env.test_state->stdout = NULL;
+		fclose(env.test_state->stdout_saved);
+		env.test_state->stdout_saved = NULL;
 	}
 #endif
 }
@@ -96,13 +114,13 @@ static void stdio_restore(void)
 		return;
 	}
 
-	if (stdout == env.stdout)
+	if (stdout == env.stdout_saved)
 		return;
 
 	stdio_restore_cleanup();
 
-	stdout = env.stdout;
-	stderr = env.stderr;
+	stdout = env.stdout_saved;
+	stderr = env.stderr_saved;
 #endif
 }
 
@@ -141,6 +159,7 @@ struct prog_test_def {
 	void (*run_serial_test)(void);
 	bool should_run;
 	bool need_cgroup_cleanup;
+	bool should_tmon;
 };
 
 /* Override C runtime library's usleep() implementation to ensure nanosleep()
@@ -178,46 +197,59 @@ static bool should_run(struct test_selector *sel, int num, const char *name)
 	return num < sel->num_set_len && sel->num_set[num];
 }
 
-static bool should_run_subtest(struct test_selector *sel,
-			       struct test_selector *subtest_sel,
-			       int subtest_num,
-			       const char *test_name,
-			       const char *subtest_name)
+static bool match_subtest(struct test_filter_set *filter,
+			  const char *test_name,
+			  const char *subtest_name)
 {
 	int i, j;
 
-	for (i = 0; i < sel->blacklist.cnt; i++) {
-		if (glob_match(test_name, sel->blacklist.tests[i].name)) {
-			if (!sel->blacklist.tests[i].subtest_cnt)
-				return false;
-
-			for (j = 0; j < sel->blacklist.tests[i].subtest_cnt; j++) {
-				if (glob_match(subtest_name,
-					       sel->blacklist.tests[i].subtests[j]))
-					return false;
-			}
-		}
-	}
-
-	for (i = 0; i < sel->whitelist.cnt; i++) {
-		if (glob_match(test_name, sel->whitelist.tests[i].name)) {
-			if (!sel->whitelist.tests[i].subtest_cnt)
+	for (i = 0; i < filter->cnt; i++) {
+		if (glob_match(test_name, filter->tests[i].name)) {
+			if (!filter->tests[i].subtest_cnt)
 				return true;
 
-			for (j = 0; j < sel->whitelist.tests[i].subtest_cnt; j++) {
+			for (j = 0; j < filter->tests[i].subtest_cnt; j++) {
 				if (glob_match(subtest_name,
-					       sel->whitelist.tests[i].subtests[j]))
+					       filter->tests[i].subtests[j]))
 					return true;
 			}
 		}
 	}
 
+	return false;
+}
+
+static bool should_run_subtest(struct test_selector *sel,
+			       struct test_selector *subtest_sel,
+			       int subtest_num,
+			       const char *test_name,
+			       const char *subtest_name)
+{
+	if (match_subtest(&sel->blacklist, test_name, subtest_name))
+		return false;
+
+	if (match_subtest(&sel->whitelist, test_name, subtest_name))
+		return true;
+
 	if (!sel->whitelist.cnt && !subtest_sel->num_set)
 		return true;
 
 	return subtest_num < subtest_sel->num_set_len && subtest_sel->num_set[subtest_num];
 }
 
+static bool should_tmon(struct test_selector *sel, const char *name)
+{
+	int i;
+
+	for (i = 0; i < sel->whitelist.cnt; i++) {
+		if (glob_match(name, sel->whitelist.tests[i].name) &&
+		    !sel->whitelist.tests[i].subtest_cnt)
+			return true;
+	}
+
+	return false;
+}
+
 static char *test_result(bool failed, bool skipped)
 {
 	return failed ? "FAIL" : (skipped ? "SKIP" : "OK");
@@ -230,25 +262,25 @@ static void print_test_result(const struct prog_test_def *test, const struct tes
 	int skipped_cnt = test_state->skip_cnt;
 	int subtests_cnt = test_state->subtest_num;
 
-	fprintf(env.stdout, "#%-*d %s:", TEST_NUM_WIDTH, test->test_num, test->test_name);
+	fprintf(env.stdout_saved, "#%-*d %s:", TEST_NUM_WIDTH, test->test_num, test->test_name);
 	if (test_state->error_cnt)
-		fprintf(env.stdout, "FAIL");
+		fprintf(env.stdout_saved, "FAIL");
 	else if (!skipped_cnt)
-		fprintf(env.stdout, "OK");
+		fprintf(env.stdout_saved, "OK");
 	else if (skipped_cnt == subtests_cnt || !subtests_cnt)
-		fprintf(env.stdout, "SKIP");
+		fprintf(env.stdout_saved, "SKIP");
 	else
-		fprintf(env.stdout, "OK (SKIP: %d/%d)", skipped_cnt, subtests_cnt);
+		fprintf(env.stdout_saved, "OK (SKIP: %d/%d)", skipped_cnt, subtests_cnt);
 
-	fprintf(env.stdout, "\n");
+	fprintf(env.stdout_saved, "\n");
 }
 
 static void print_test_log(char *log_buf, size_t log_cnt)
 {
 	log_buf[log_cnt] = '\0';
-	fprintf(env.stdout, "%s", log_buf);
+	fprintf(env.stdout_saved, "%s", log_buf);
 	if (log_buf[log_cnt - 1] != '\n')
-		fprintf(env.stdout, "\n");
+		fprintf(env.stdout_saved, "\n");
 }
 
 static void print_subtest_name(int test_num, int subtest_num,
@@ -259,14 +291,14 @@ static void print_subtest_name(int test_num, int subtest_num,
 
 	snprintf(test_num_str, sizeof(test_num_str), "%d/%d", test_num, subtest_num);
 
-	fprintf(env.stdout, "#%-*s %s/%s",
+	fprintf(env.stdout_saved, "#%-*s %s/%s",
 		TEST_NUM_WIDTH, test_num_str,
 		test_name, subtest_name);
 
 	if (result)
-		fprintf(env.stdout, ":%s", result);
+		fprintf(env.stdout_saved, ":%s", result);
 
-	fprintf(env.stdout, "\n");
+	fprintf(env.stdout_saved, "\n");
 }
 
 static void jsonw_write_log_message(json_writer_t *w, char *log_buf, size_t log_cnt)
@@ -451,7 +483,7 @@ bool test__start_subtest(const char *subtest_name)
 	memset(subtest_state, 0, sub_state_size);
 
 	if (!subtest_name || !subtest_name[0]) {
-		fprintf(env.stderr,
+		fprintf(env.stderr_saved,
 			"Subtest #%d didn't provide sub-test name!\n",
 			state->subtest_num);
 		return false;
@@ -459,7 +491,7 @@ bool test__start_subtest(const char *subtest_name)
 
 	subtest_state->name = strdup(subtest_name);
 	if (!subtest_state->name) {
-		fprintf(env.stderr,
+		fprintf(env.stderr_saved,
 			"Subtest #%d: failed to copy subtest name!\n",
 			state->subtest_num);
 		return false;
@@ -474,6 +506,10 @@ bool test__start_subtest(const char *subtest_name)
 		return false;
 	}
 
+	subtest_state->should_tmon = match_subtest(&env.tmon_selector.whitelist,
+						   test->test_name,
+						   subtest_name);
+
 	env.subtest_state = subtest_state;
 	stdio_hijack_init(&subtest_state->log_buf, &subtest_state->log_cnt);
 
@@ -610,6 +646,92 @@ out:
 	return err;
 }
 
+struct netns_obj {
+	char *nsname;
+	struct tmonitor_ctx *tmon;
+	struct nstoken *nstoken;
+};
+
+/* Create a new network namespace with the given name.
+ *
+ * Create a new network namespace and set the network namespace of the
+ * current process to the new network namespace if the argument "open" is
+ * true. This function should be paired with netns_free() to release the
+ * resource and delete the network namespace.
+ *
+ * It also implements the functionality of the option "-m" by starting
+ * traffic monitor on the background to capture the packets in this network
+ * namespace if the current test or subtest matching the pattern.
+ *
+ * nsname: the name of the network namespace to create.
+ * open: open the network namespace if true.
+ *
+ * Return: the network namespace object on success, NULL on failure.
+ */
+struct netns_obj *netns_new(const char *nsname, bool open)
+{
+	struct netns_obj *netns_obj = malloc(sizeof(*netns_obj));
+	const char *test_name, *subtest_name;
+	int r;
+
+	if (!netns_obj)
+		return NULL;
+	memset(netns_obj, 0, sizeof(*netns_obj));
+
+	netns_obj->nsname = strdup(nsname);
+	if (!netns_obj->nsname)
+		goto fail;
+
+	/* Create the network namespace */
+	r = make_netns(nsname);
+	if (r)
+		goto fail;
+
+	/* Start traffic monitor */
+	if (env.test->should_tmon ||
+	    (env.subtest_state && env.subtest_state->should_tmon)) {
+		test_name = env.test->test_name;
+		subtest_name = env.subtest_state ? env.subtest_state->name : NULL;
+		netns_obj->tmon = traffic_monitor_start(nsname, test_name, subtest_name);
+		if (!netns_obj->tmon) {
+			fprintf(stderr, "Failed to start traffic monitor for %s\n", nsname);
+			goto fail;
+		}
+	} else {
+		netns_obj->tmon = NULL;
+	}
+
+	if (open) {
+		netns_obj->nstoken = open_netns(nsname);
+		if (!netns_obj->nstoken)
+			goto fail;
+	}
+
+	return netns_obj;
+fail:
+	traffic_monitor_stop(netns_obj->tmon);
+	remove_netns(nsname);
+	free(netns_obj->nsname);
+	free(netns_obj);
+	return NULL;
+}
+
+/* Delete the network namespace.
+ *
+ * This function should be paired with netns_new() to delete the namespace
+ * created by netns_new().
+ */
+void netns_free(struct netns_obj *netns_obj)
+{
+	if (!netns_obj)
+		return;
+	traffic_monitor_stop(netns_obj->tmon);
+	close_netns(netns_obj->nstoken);
+	remove_netns(netns_obj->nsname);
+	free(netns_obj->nsname);
+	free(netns_obj);
+}
+
 /* extern declarations for test funcs */
 #define DEFINE_TEST(name)				\
 	extern void test_##name(void) __weak;		\
@@ -653,7 +775,8 @@ enum ARG_KEYS {
 	ARG_TEST_NAME_GLOB_DENYLIST = 'd',
 	ARG_NUM_WORKERS = 'j',
 	ARG_DEBUG = -1,
-	ARG_JSON_SUMMARY = 'J'
+	ARG_JSON_SUMMARY = 'J',
+	ARG_TRAFFIC_MONITOR = 'm',
 };
 
 static const struct argp_option opts[] = {
@@ -680,6 +803,10 @@ static const struct argp_option opts[] = {
 	{ "debug", ARG_DEBUG, NULL, 0,
 	  "print extra debug information for test_progs." },
 	{ "json-summary", ARG_JSON_SUMMARY, "FILE", 0, "Write report in json format to this file."},
+#ifdef TRAFFIC_MONITOR
+	{ "traffic-monitor", ARG_TRAFFIC_MONITOR, "NAMES", 0,
+	  "Monitor network traffic of tests with name matching the pattern (supports '*' wildcard)." },
+#endif
 	{},
 };
 
@@ -848,6 +975,7 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 				return -EINVAL;
 			}
 		}
+		env_verbosity = env->verbosity;
 
 		if (verbose()) {
 			if (setenv("SELFTESTS_VERBOSE", "1", 1) == -1) {
@@ -891,6 +1019,18 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 		break;
 	case ARGP_KEY_END:
 		break;
+#ifdef TRAFFIC_MONITOR
+	case ARG_TRAFFIC_MONITOR:
+		if (arg[0] == '@')
+			err = parse_test_list_file(arg + 1,
+						   &env->tmon_selector.whitelist,
+						   true);
+		else
+			err = parse_test_list(arg,
+					      &env->tmon_selector.whitelist,
+					      true);
+		break;
+#endif
 	default:
 		return ARGP_ERR_UNKNOWN;
 	}
@@ -1029,7 +1169,7 @@ void crash_handler(int signum)
 
 	sz = backtrace(bt, ARRAY_SIZE(bt));
 
-	if (env.stdout)
+	if (env.stdout_saved)
 		stdio_restore();
 	if (env.test) {
 		env.test_state->error_cnt++;
@@ -1345,7 +1485,7 @@ static void calculate_summary_and_print_errors(struct test_env *env)
 	if (env->json) {
 		w = jsonw_new(env->json);
 		if (!w)
-			fprintf(env->stderr, "Failed to create new JSON stream.");
+			fprintf(env->stderr_saved, "Failed to create new JSON stream.");
 	}
 
 	if (w) {
@@ -1360,7 +1500,7 @@ static void calculate_summary_and_print_errors(struct test_env *env)
 
 	/*
 	 * We only print error logs summary when there are failed tests and
-	 * verbose mode is not enabled. Otherwise, results may be incosistent.
+	 * verbose mode is not enabled. Otherwise, results may be inconsistent.
 	 *
 	 */
 	if (!verbose() && fail_cnt) {
@@ -1694,8 +1834,8 @@ int main(int argc, char **argv)
 		return -1;
 	}
 
-	env.stdout = stdout;
-	env.stderr = stderr;
+	env.stdout_saved = stdout;
+	env.stderr_saved = stderr;
 
 	env.has_testmod = true;
 	if (!env.list_test_names) {
@@ -1703,7 +1843,7 @@ int main(int argc, char **argv)
 		unload_bpf_testmod(verbose());
 
 		if (load_bpf_testmod(verbose())) {
-			fprintf(env.stderr, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n");
+			fprintf(env.stderr_saved, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n");
 			env.has_testmod = false;
 		}
 	}
@@ -1722,6 +1862,8 @@ int main(int argc, char **argv)
 				test->test_num, test->test_name, test->test_name, test->test_name);
 			exit(EXIT_ERR_SETUP_INFRA);
 		}
+		if (test->should_run)
+			test->should_tmon = should_tmon(&env.tmon_selector, test->test_name);
 	}
 
 	/* ignore workers if we are just listing */
@@ -1731,7 +1873,7 @@ int main(int argc, char **argv)
 	/* launch workers if requested */
 	env.worker_id = -1; /* main process */
 	if (env.workers) {
-		env.worker_pids = calloc(sizeof(__pid_t), env.workers);
+		env.worker_pids = calloc(sizeof(pid_t), env.workers);
 		env.worker_socks = calloc(sizeof(int), env.workers);
 		if (env.debug)
 			fprintf(stdout, "Launching %d workers.\n", env.workers);
@@ -1781,7 +1923,7 @@ int main(int argc, char **argv)
 		}
 
 		if (env.list_test_names) {
-			fprintf(env.stdout, "%s\n", test->test_name);
+			fprintf(env.stdout_saved, "%s\n", test->test_name);
 			env.succ_cnt++;
 			continue;
 		}
@@ -1806,6 +1948,7 @@ out:
 
 	free_test_selector(&env.test_selector);
 	free_test_selector(&env.subtest_selector);
+	free_test_selector(&env.tmon_selector);
 	free_test_states();
 
 	if (env.succ_cnt + env.fail_cnt + env.skip_cnt == 0)
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 51341d50213b..7767d9a825ae 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -74,8 +74,9 @@ struct subtest_state {
 	int error_cnt;
 	bool skipped;
 	bool filtered;
+	bool should_tmon;
 
-	FILE *stdout;
+	FILE *stdout_saved;
 };
 
 struct test_state {
@@ -92,12 +93,15 @@ struct test_state {
 	size_t log_cnt;
 	char *log_buf;
 
-	FILE *stdout;
+	FILE *stdout_saved;
 };
 
+extern int env_verbosity;
+
 struct test_env {
 	struct test_selector test_selector;
 	struct test_selector subtest_selector;
+	struct test_selector tmon_selector;
 	bool verifier_stats;
 	bool debug;
 	enum verbosity verbosity;
@@ -111,8 +115,8 @@ struct test_env {
 	struct test_state *test_state; /* current running test state */
 	struct subtest_state *subtest_state; /* current running subtest state */
 
-	FILE *stdout;
-	FILE *stderr;
+	FILE *stdout_saved;
+	FILE *stderr_saved;
 	int nr_cpus;
 	FILE *json;
 
@@ -428,6 +432,10 @@ int write_sysctl(const char *sysctl, const char *value);
 int get_bpf_max_tramp_links_from(struct btf *btf);
 int get_bpf_max_tramp_links(void);
 
+struct netns_obj;
+struct netns_obj *netns_new(const char *name, bool open);
+void netns_free(struct netns_obj *netns);
+
 #ifdef __x86_64__
 #define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep"
 #elif defined(__s390x__)
@@ -447,7 +455,6 @@ typedef int (*pre_execution_cb)(struct bpf_object *obj);
 struct test_loader {
 	char *log_buf;
 	size_t log_buf_sz;
-	size_t next_match_pos;
 	pre_execution_cb pre_execution_cb;
 
 	struct bpf_object *obj;
diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id.sh b/tools/testing/selftests/bpf/test_skb_cgroup_id.sh
deleted file mode 100755
index 515c2eafc97f..000000000000
--- a/tools/testing/selftests/bpf/test_skb_cgroup_id.sh
+++ /dev/null
@@ -1,63 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-# Copyright (c) 2018 Facebook
-
-set -eu
-
-wait_for_ip()
-{
-	local _i
-	echo -n "Wait for testing link-local IP to become available "
-	for _i in $(seq ${MAX_PING_TRIES}); do
-		echo -n "."
-		if $PING6 -c 1 -W 1 ff02::1%${TEST_IF} >/dev/null 2>&1; then
-			echo " OK"
-			return
-		fi
-		sleep 1
-	done
-	echo 1>&2 "ERROR: Timeout waiting for test IP to become available."
-	exit 1
-}
-
-setup()
-{
-	# Create testing interfaces not to interfere with current environment.
-	ip link add dev ${TEST_IF} type veth peer name ${TEST_IF_PEER}
-	ip link set ${TEST_IF} up
-	ip link set ${TEST_IF_PEER} up
-
-	wait_for_ip
-
-	tc qdisc add dev ${TEST_IF} clsact
-	tc filter add dev ${TEST_IF} egress bpf obj ${BPF_PROG_OBJ} \
-		sec ${BPF_PROG_SECTION} da
-
-	BPF_PROG_ID=$(tc filter show dev ${TEST_IF} egress | \
-			awk '/ id / {sub(/.* id /, "", $0); print($1)}')
-}
-
-cleanup()
-{
-	ip link del ${TEST_IF} 2>/dev/null || :
-	ip link del ${TEST_IF_PEER} 2>/dev/null || :
-}
-
-main()
-{
-	trap cleanup EXIT 2 3 6 15
-	setup
-	${PROG} ${TEST_IF} ${BPF_PROG_ID}
-}
-
-DIR=$(dirname $0)
-TEST_IF="test_cgid_1"
-TEST_IF_PEER="test_cgid_2"
-MAX_PING_TRIES=5
-BPF_PROG_OBJ="${DIR}/test_skb_cgroup_id_kern.bpf.o"
-BPF_PROG_SECTION="cgroup_id_logger"
-BPF_PROG_ID=0
-PROG="${DIR}/test_skb_cgroup_id_user"
-type ping6 >/dev/null 2>&1 && PING6="ping6" || PING6="ping -6"
-
-main
diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c b/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c
deleted file mode 100644
index ed518d075d1d..000000000000
--- a/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c
+++ /dev/null
@@ -1,183 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (c) 2018 Facebook
-
-#include <stdlib.h>
-#include <string.h>
-#include <unistd.h>
-
-#include <arpa/inet.h>
-#include <net/if.h>
-#include <netinet/in.h>
-#include <sys/socket.h>
-#include <sys/types.h>
-
-
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include "cgroup_helpers.h"
-
-#define CGROUP_PATH		"/skb_cgroup_test"
-#define NUM_CGROUP_LEVELS	4
-
-/* RFC 4291, Section 2.7.1 */
-#define LINKLOCAL_MULTICAST	"ff02::1"
-
-static int mk_dst_addr(const char *ip, const char *iface,
-		       struct sockaddr_in6 *dst)
-{
-	memset(dst, 0, sizeof(*dst));
-
-	dst->sin6_family = AF_INET6;
-	dst->sin6_port = htons(1025);
-
-	if (inet_pton(AF_INET6, ip, &dst->sin6_addr) != 1) {
-		log_err("Invalid IPv6: %s", ip);
-		return -1;
-	}
-
-	dst->sin6_scope_id = if_nametoindex(iface);
-	if (!dst->sin6_scope_id) {
-		log_err("Failed to get index of iface: %s", iface);
-		return -1;
-	}
-
-	return 0;
-}
-
-static int send_packet(const char *iface)
-{
-	struct sockaddr_in6 dst;
-	char msg[] = "msg";
-	int err = 0;
-	int fd = -1;
-
-	if (mk_dst_addr(LINKLOCAL_MULTICAST, iface, &dst))
-		goto err;
-
-	fd = socket(AF_INET6, SOCK_DGRAM, 0);
-	if (fd == -1) {
-		log_err("Failed to create UDP socket");
-		goto err;
-	}
-
-	if (sendto(fd, &msg, sizeof(msg), 0, (const struct sockaddr *)&dst,
-		   sizeof(dst)) == -1) {
-		log_err("Failed to send datagram");
-		goto err;
-	}
-
-	goto out;
-err:
-	err = -1;
-out:
-	if (fd >= 0)
-		close(fd);
-	return err;
-}
-
-int get_map_fd_by_prog_id(int prog_id)
-{
-	struct bpf_prog_info info = {};
-	__u32 info_len = sizeof(info);
-	__u32 map_ids[1];
-	int prog_fd = -1;
-	int map_fd = -1;
-
-	prog_fd = bpf_prog_get_fd_by_id(prog_id);
-	if (prog_fd < 0) {
-		log_err("Failed to get fd by prog id %d", prog_id);
-		goto err;
-	}
-
-	info.nr_map_ids = 1;
-	info.map_ids = (__u64) (unsigned long) map_ids;
-
-	if (bpf_prog_get_info_by_fd(prog_fd, &info, &info_len)) {
-		log_err("Failed to get info by prog fd %d", prog_fd);
-		goto err;
-	}
-
-	if (!info.nr_map_ids) {
-		log_err("No maps found for prog fd %d", prog_fd);
-		goto err;
-	}
-
-	map_fd = bpf_map_get_fd_by_id(map_ids[0]);
-	if (map_fd < 0)
-		log_err("Failed to get fd by map id %d", map_ids[0]);
-err:
-	if (prog_fd >= 0)
-		close(prog_fd);
-	return map_fd;
-}
-
-int check_ancestor_cgroup_ids(int prog_id)
-{
-	__u64 actual_ids[NUM_CGROUP_LEVELS], expected_ids[NUM_CGROUP_LEVELS];
-	__u32 level;
-	int err = 0;
-	int map_fd;
-
-	expected_ids[0] = get_cgroup_id("/..");	/* root cgroup */
-	expected_ids[1] = get_cgroup_id("");
-	expected_ids[2] = get_cgroup_id(CGROUP_PATH);
-	expected_ids[3] = 0; /* non-existent cgroup */
-
-	map_fd = get_map_fd_by_prog_id(prog_id);
-	if (map_fd < 0)
-		goto err;
-
-	for (level = 0; level < NUM_CGROUP_LEVELS; ++level) {
-		if (bpf_map_lookup_elem(map_fd, &level, &actual_ids[level])) {
-			log_err("Failed to lookup key %d", level);
-			goto err;
-		}
-		if (actual_ids[level] != expected_ids[level]) {
-			log_err("%llx (actual) != %llx (expected), level: %u\n",
-				actual_ids[level], expected_ids[level], level);
-			goto err;
-		}
-	}
-
-	goto out;
-err:
-	err = -1;
-out:
-	if (map_fd >= 0)
-		close(map_fd);
-	return err;
-}
-
-int main(int argc, char **argv)
-{
-	int cgfd = -1;
-	int err = 0;
-
-	if (argc < 3) {
-		fprintf(stderr, "Usage: %s iface prog_id\n", argv[0]);
-		exit(EXIT_FAILURE);
-	}
-
-	/* Use libbpf 1.0 API mode */
-	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
-
-	cgfd = cgroup_setup_and_join(CGROUP_PATH);
-	if (cgfd < 0)
-		goto err;
-
-	if (send_packet(argv[1]))
-		goto err;
-
-	if (check_ancestor_cgroup_ids(atoi(argv[2])))
-		goto err;
-
-	goto out;
-err:
-	err = -1;
-out:
-	close(cgfd);
-	cleanup_cgroup_environment();
-	printf("[%s]\n", err ? "FAIL" : "PASS");
-	return err;
-}
diff --git a/tools/testing/selftests/bpf/test_xdp_veth.sh b/tools/testing/selftests/bpf/test_xdp_veth.sh
deleted file mode 100755
index 5211ca9a0239..000000000000
--- a/tools/testing/selftests/bpf/test_xdp_veth.sh
+++ /dev/null
@@ -1,121 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-#
-# Create 3 namespaces with 3 veth peers, and
-# forward packets in-between using native XDP
-#
-#                      XDP_TX
-# NS1(veth11)        NS2(veth22)        NS3(veth33)
-#      |                  |                  |
-#      |                  |                  |
-#   (veth1,            (veth2,            (veth3,
-#   id:111)            id:122)            id:133)
-#     ^ |                ^ |                ^ |
-#     | |  XDP_REDIRECT  | |  XDP_REDIRECT  | |
-#     | ------------------ ------------------ |
-#     -----------------------------------------
-#                    XDP_REDIRECT
-
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
-TESTNAME=xdp_veth
-BPF_FS=$(awk '$3 == "bpf" {print $2; exit}' /proc/mounts)
-BPF_DIR=$BPF_FS/test_$TESTNAME
-readonly NS1="ns1-$(mktemp -u XXXXXX)"
-readonly NS2="ns2-$(mktemp -u XXXXXX)"
-readonly NS3="ns3-$(mktemp -u XXXXXX)"
-
-_cleanup()
-{
-	set +e
-	ip link del veth1 2> /dev/null
-	ip link del veth2 2> /dev/null
-	ip link del veth3 2> /dev/null
-	ip netns del ${NS1} 2> /dev/null
-	ip netns del ${NS2} 2> /dev/null
-	ip netns del ${NS3} 2> /dev/null
-	rm -rf $BPF_DIR 2> /dev/null
-}
-
-cleanup_skip()
-{
-	echo "selftests: $TESTNAME [SKIP]"
-	_cleanup
-
-	exit $ksft_skip
-}
-
-cleanup()
-{
-	if [ "$?" = 0 ]; then
-		echo "selftests: $TESTNAME [PASS]"
-	else
-		echo "selftests: $TESTNAME [FAILED]"
-	fi
-	_cleanup
-}
-
-if [ $(id -u) -ne 0 ]; then
-	echo "selftests: $TESTNAME [SKIP] Need root privileges"
-	exit $ksft_skip
-fi
-
-if ! ip link set dev lo xdp off > /dev/null 2>&1; then
-	echo "selftests: $TESTNAME [SKIP] Could not run test without the ip xdp support"
-	exit $ksft_skip
-fi
-
-if [ -z "$BPF_FS" ]; then
-	echo "selftests: $TESTNAME [SKIP] Could not run test without bpffs mounted"
-	exit $ksft_skip
-fi
-
-if ! bpftool version > /dev/null 2>&1; then
-	echo "selftests: $TESTNAME [SKIP] Could not run test without bpftool"
-	exit $ksft_skip
-fi
-
-set -e
-
-trap cleanup_skip EXIT
-
-ip netns add ${NS1}
-ip netns add ${NS2}
-ip netns add ${NS3}
-
-ip link add veth1 index 111 type veth peer name veth11 netns ${NS1}
-ip link add veth2 index 122 type veth peer name veth22 netns ${NS2}
-ip link add veth3 index 133 type veth peer name veth33 netns ${NS3}
-
-ip link set veth1 up
-ip link set veth2 up
-ip link set veth3 up
-
-ip -n ${NS1} addr add 10.1.1.11/24 dev veth11
-ip -n ${NS3} addr add 10.1.1.33/24 dev veth33
-
-ip -n ${NS1} link set dev veth11 up
-ip -n ${NS2} link set dev veth22 up
-ip -n ${NS3} link set dev veth33 up
-
-mkdir $BPF_DIR
-bpftool prog loadall \
-	xdp_redirect_map.bpf.o $BPF_DIR/progs type xdp \
-	pinmaps $BPF_DIR/maps
-bpftool map update pinned $BPF_DIR/maps/tx_port key 0 0 0 0 value 122 0 0 0
-bpftool map update pinned $BPF_DIR/maps/tx_port key 1 0 0 0 value 133 0 0 0
-bpftool map update pinned $BPF_DIR/maps/tx_port key 2 0 0 0 value 111 0 0 0
-ip link set dev veth1 xdp pinned $BPF_DIR/progs/xdp_redirect_map_0
-ip link set dev veth2 xdp pinned $BPF_DIR/progs/xdp_redirect_map_1
-ip link set dev veth3 xdp pinned $BPF_DIR/progs/xdp_redirect_map_2
-
-ip -n ${NS1} link set dev veth11 xdp obj xdp_dummy.bpf.o sec xdp
-ip -n ${NS2} link set dev veth22 xdp obj xdp_tx.bpf.o sec xdp
-ip -n ${NS3} link set dev veth33 xdp obj xdp_dummy.bpf.o sec xdp
-
-trap cleanup EXIT
-
-ip netns exec ${NS1} ping -c 1 -W 1 10.1.1.33
-
-exit 0
diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c
index d5379a0e6da8..d3c3c3a24150 100644
--- a/tools/testing/selftests/bpf/testing_helpers.c
+++ b/tools/testing/selftests/bpf/testing_helpers.c
@@ -7,6 +7,7 @@
 #include <errno.h>
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
+#include "disasm.h"
 #include "test_progs.h"
 #include "testing_helpers.h"
 #include <linux/membarrier.h>
@@ -220,13 +221,13 @@ int parse_test_list(const char *s,
 		    bool is_glob_pattern)
 {
 	char *input, *state = NULL, *test_spec;
-	int err = 0;
+	int err = 0, cnt = 0;
 
 	input = strdup(s);
 	if (!input)
 		return -ENOMEM;
 
-	while ((test_spec = strtok_r(state ? NULL : input, ",", &state))) {
+	while ((test_spec = strtok_r(cnt++ ? NULL : input, ",", &state))) {
 		err = insert_test(set, test_spec, is_glob_pattern);
 		if (err)
 			break;
@@ -451,7 +452,7 @@ int get_xlated_program(int fd_prog, struct bpf_insn **buf, __u32 *cnt)
 
 	*cnt = xlated_prog_len / buf_element_size;
 	*buf = calloc(*cnt, buf_element_size);
-	if (!buf) {
+	if (!*buf) {
 		perror("can't allocate xlated program buffer");
 		return -ENOMEM;
 	}
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 465d196c7165..2d742fdac6b9 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -10,6 +10,8 @@
 #include <pthread.h>
 #include <unistd.h>
 #include <linux/perf_event.h>
+#include <linux/fs.h>
+#include <sys/ioctl.h>
 #include <sys/mman.h>
 #include "trace_helpers.h"
 #include <linux/limits.h>
@@ -244,29 +246,91 @@ out:
 	return err;
 }
 
+#ifdef PROCMAP_QUERY
+int env_verbosity __weak = 0;
+
+static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags)
+{
+	char path_buf[PATH_MAX], build_id_buf[20];
+	struct procmap_query q;
+	int err;
+
+	memset(&q, 0, sizeof(q));
+	q.size = sizeof(q);
+	q.query_flags = query_flags;
+	q.query_addr = (__u64)addr;
+	q.vma_name_addr = (__u64)path_buf;
+	q.vma_name_size = sizeof(path_buf);
+	q.build_id_addr = (__u64)build_id_buf;
+	q.build_id_size = sizeof(build_id_buf);
+
+	err = ioctl(fd, PROCMAP_QUERY, &q);
+	if (err < 0) {
+		err = -errno;
+		if (err == -ENOTTY)
+			return -EOPNOTSUPP; /* ioctl() not implemented yet */
+		if (err == -ENOENT)
+			return -ESRCH; /* vma not found */
+		return err;
+	}
+
+	if (env_verbosity >= 1) {
+		printf("VMA FOUND (addr %08lx): %08lx-%08lx %c%c%c%c %08lx %02x:%02x %ld %s (build ID: %s, %d bytes)\n",
+		       (long)addr, (long)q.vma_start, (long)q.vma_end,
+		       (q.vma_flags & PROCMAP_QUERY_VMA_READABLE) ? 'r' : '-',
+		       (q.vma_flags & PROCMAP_QUERY_VMA_WRITABLE) ? 'w' : '-',
+		       (q.vma_flags & PROCMAP_QUERY_VMA_EXECUTABLE) ? 'x' : '-',
+		       (q.vma_flags & PROCMAP_QUERY_VMA_SHARED) ? 's' : 'p',
+		       (long)q.vma_offset, q.dev_major, q.dev_minor, (long)q.inode,
+		       q.vma_name_size ? path_buf : "",
+		       q.build_id_size ? "YES" : "NO",
+		       q.build_id_size);
+	}
+
+	*start = q.vma_start;
+	*offset = q.vma_offset;
+	*flags = q.vma_flags;
+	return 0;
+}
+#else
+static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 ssize_t get_uprobe_offset(const void *addr)
 {
-	size_t start, end, base;
-	char buf[256];
-	bool found = false;
+	size_t start, base, end;
 	FILE *f;
+	char buf[256];
+	int err, flags;
 
 	f = fopen("/proc/self/maps", "r");
 	if (!f)
 		return -errno;
 
-	while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &base) == 4) {
-		if (buf[2] == 'x' && (uintptr_t)addr >= start && (uintptr_t)addr < end) {
-			found = true;
-			break;
+	/* requested executable VMA only */
+	err = procmap_query(fileno(f), addr, PROCMAP_QUERY_VMA_EXECUTABLE, &start, &base, &flags);
+	if (err == -EOPNOTSUPP) {
+		bool found = false;
+
+		while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &base) == 4) {
+			if (buf[2] == 'x' && (uintptr_t)addr >= start && (uintptr_t)addr < end) {
+				found = true;
+				break;
+			}
+		}
+		if (!found) {
+			fclose(f);
+			return -ESRCH;
 		}
+	} else if (err) {
+		fclose(f);
+		return err;
 	}
-
 	fclose(f);
 
-	if (!found)
-		return -ESRCH;
-
 #if defined(__powerpc64__) && defined(_CALL_ELF) && _CALL_ELF == 2
 
 #define OP_RT_RA_MASK   0xffff0000UL
@@ -307,15 +371,25 @@ ssize_t get_rel_offset(uintptr_t addr)
 	size_t start, end, offset;
 	char buf[256];
 	FILE *f;
+	int err, flags;
 
 	f = fopen("/proc/self/maps", "r");
 	if (!f)
 		return -errno;
 
-	while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &offset) == 4) {
-		if (addr >= start && addr < end) {
-			fclose(f);
-			return (size_t)addr - start + offset;
+	err = procmap_query(fileno(f), (const void *)addr, 0, &start, &offset, &flags);
+	if (err == 0) {
+		fclose(f);
+		return (size_t)addr - start + offset;
+	} else if (err != -EOPNOTSUPP) {
+		fclose(f);
+		return err;
+	} else if (err) {
+		while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &offset) == 4) {
+			if (addr >= start && addr < end) {
+				fclose(f);
+				return (size_t)addr - start + offset;
+			}
 		}
 	}
 
diff --git a/tools/testing/selftests/bpf/unpriv_helpers.c b/tools/testing/selftests/bpf/unpriv_helpers.c
index b6d016461fb0..220f6a963813 100644
--- a/tools/testing/selftests/bpf/unpriv_helpers.c
+++ b/tools/testing/selftests/bpf/unpriv_helpers.c
@@ -2,7 +2,6 @@
 
 #include <stdbool.h>
 #include <stdlib.h>
-#include <error.h>
 #include <stdio.h>
 #include <string.h>
 #include <unistd.h>
diff --git a/tools/testing/selftests/bpf/uprobe_multi.c b/tools/testing/selftests/bpf/uprobe_multi.c
index 7ffa563ffeba..c7828b13e5ff 100644
--- a/tools/testing/selftests/bpf/uprobe_multi.c
+++ b/tools/testing/selftests/bpf/uprobe_multi.c
@@ -2,8 +2,21 @@
 
 #include <stdio.h>
 #include <string.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <sys/mman.h>
+#include <unistd.h>
 #include <sdt.h>
 
+#ifndef MADV_POPULATE_READ
+#define MADV_POPULATE_READ 22
+#endif
+
+int __attribute__((weak)) uprobe(void)
+{
+	return 0;
+}
+
 #define __PASTE(a, b) a##b
 #define PASTE(a, b) __PASTE(a, b)
 
@@ -75,6 +88,30 @@ static int usdt(void)
 	return 0;
 }
 
+extern char build_id_start[];
+extern char build_id_end[];
+
+int __attribute__((weak)) trigger_uprobe(bool build_id_resident)
+{
+	int page_sz = sysconf(_SC_PAGESIZE);
+	void *addr;
+
+	/* page-align build ID start */
+	addr = (void *)((uintptr_t)&build_id_start & ~(page_sz - 1));
+
+	/* to guarantee MADV_PAGEOUT work reliably, we need to ensure that
+	 * memory range is mapped into current process, so we unconditionally
+	 * do MADV_POPULATE_READ, and then MADV_PAGEOUT, if necessary
+	 */
+	madvise(addr, page_sz, MADV_POPULATE_READ);
+	if (!build_id_resident)
+		madvise(addr, page_sz, MADV_PAGEOUT);
+
+	(void)uprobe();
+
+	return 0;
+}
+
 int main(int argc, char **argv)
 {
 	if (argc != 2)
@@ -84,6 +121,10 @@ int main(int argc, char **argv)
 		return bench();
 	if (!strcmp("usdt", argv[1]))
 		return usdt();
+	if (!strcmp("uprobe-paged-out", argv[1]))
+		return trigger_uprobe(false /* page-out build ID */);
+	if (!strcmp("uprobe-paged-in", argv[1]))
+		return trigger_uprobe(true /* page-in build ID */);
 
 error:
 	fprintf(stderr, "usage: %s <bench|usdt>\n", argv[0]);
diff --git a/tools/testing/selftests/bpf/uprobe_multi.ld b/tools/testing/selftests/bpf/uprobe_multi.ld
new file mode 100644
index 000000000000..a2e94828bc8c
--- /dev/null
+++ b/tools/testing/selftests/bpf/uprobe_multi.ld
@@ -0,0 +1,11 @@
+SECTIONS
+{
+	. = ALIGN(4096);
+	.note.gnu.build-id : { *(.note.gnu.build-id) }
+	. = ALIGN(4096);
+}
+INSERT AFTER .text;
+
+build_id_start = ADDR(.note.gnu.build-id);
+build_id_end = ADDR(.note.gnu.build-id) + SIZEOF(.note.gnu.build-id);
+
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index d0cdd156cd55..7afc2619ab14 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -76,7 +76,7 @@
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = REJECT,
-	.errstr = "arg#0 expected pointer to ctx, but got PTR",
+	.errstr = "arg#0 expected pointer to ctx, but got fp",
 	.fixup_kfunc_btf_id = {
 		{ "bpf_kfunc_call_test_pass_ctx", 2 },
 	},
diff --git a/tools/testing/selftests/bpf/verifier/map_kptr.c b/tools/testing/selftests/bpf/verifier/map_kptr.c
index d25c3e9605f1..f420c0312aa0 100644
--- a/tools/testing/selftests/bpf/verifier/map_kptr.c
+++ b/tools/testing/selftests/bpf/verifier/map_kptr.c
@@ -153,7 +153,7 @@
 	.result = REJECT,
 	.errstr = "variable untrusted_ptr_ access var_off=(0x0; 0x7) disallowed",
 },
-/* Tests for unreferened PTR_TO_BTF_ID */
+/* Tests for unreferenced PTR_TO_BTF_ID */
 {
 	"map_kptr: unref: reject btf_struct_ids_match == false",
 	.insns = {
diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c
index 90643ccc221d..59a020c35647 100644
--- a/tools/testing/selftests/bpf/verifier/precise.c
+++ b/tools/testing/selftests/bpf/verifier/precise.c
@@ -39,11 +39,11 @@
 	.result = VERBOSE_ACCEPT,
 	.errstr =
 	"mark_precise: frame0: last_idx 26 first_idx 20\
-	mark_precise: frame0: regs=r2,r9 stack= before 25\
-	mark_precise: frame0: regs=r2,r9 stack= before 24\
-	mark_precise: frame0: regs=r2,r9 stack= before 23\
-	mark_precise: frame0: regs=r2,r9 stack= before 22\
-	mark_precise: frame0: regs=r2,r9 stack= before 20\
+	mark_precise: frame0: regs=r2 stack= before 25\
+	mark_precise: frame0: regs=r2 stack= before 24\
+	mark_precise: frame0: regs=r2 stack= before 23\
+	mark_precise: frame0: regs=r2 stack= before 22\
+	mark_precise: frame0: regs=r2 stack= before 20\
 	mark_precise: frame0: parent state regs=r2,r9 stack=:\
 	mark_precise: frame0: last_idx 19 first_idx 10\
 	mark_precise: frame0: regs=r2,r9 stack= before 19\
@@ -100,13 +100,13 @@
 	.errstr =
 	"26: (85) call bpf_probe_read_kernel#113\
 	mark_precise: frame0: last_idx 26 first_idx 22\
-	mark_precise: frame0: regs=r2,r9 stack= before 25\
-	mark_precise: frame0: regs=r2,r9 stack= before 24\
-	mark_precise: frame0: regs=r2,r9 stack= before 23\
-	mark_precise: frame0: regs=r2,r9 stack= before 22\
-	mark_precise: frame0: parent state regs=r2,r9 stack=:\
+	mark_precise: frame0: regs=r2 stack= before 25\
+	mark_precise: frame0: regs=r2 stack= before 24\
+	mark_precise: frame0: regs=r2 stack= before 23\
+	mark_precise: frame0: regs=r2 stack= before 22\
+	mark_precise: frame0: parent state regs=r2 stack=:\
 	mark_precise: frame0: last_idx 20 first_idx 20\
-	mark_precise: frame0: regs=r2,r9 stack= before 20\
+	mark_precise: frame0: regs=r2 stack= before 20\
 	mark_precise: frame0: parent state regs=r2,r9 stack=:\
 	mark_precise: frame0: last_idx 19 first_idx 17\
 	mark_precise: frame0: regs=r2,r9 stack= before 19\
@@ -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=-8:\
+	mark_precise: frame0: parent state regs=r4 stack=:\
 	mark_precise: frame0: last_idx 6 first_idx 4\
-	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=r4 stack= before 6: (b7) r0 = -1\
+	mark_precise: frame0: regs=r4 stack= 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/veristat.c b/tools/testing/selftests/bpf/veristat.c
index b2854238d4a0..1ec5c4c47235 100644
--- a/tools/testing/selftests/bpf/veristat.c
+++ b/tools/testing/selftests/bpf/veristat.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
 #define _GNU_SOURCE
 #include <argp.h>
+#include <libgen.h>
 #include <string.h>
 #include <stdlib.h>
 #include <sched.h>
@@ -784,13 +785,13 @@ static int parse_stat(const char *stat_name, struct stat_specs *specs)
 static int parse_stats(const char *stats_str, struct stat_specs *specs)
 {
 	char *input, *state = NULL, *next;
-	int err;
+	int err, cnt = 0;
 
 	input = strdup(stats_str);
 	if (!input)
 		return -ENOMEM;
 
-	while ((next = strtok_r(state ? NULL : input, ",", &state))) {
+	while ((next = strtok_r(cnt++ ? NULL : input, ",", &state))) {
 		err = parse_stat(next, specs);
 		if (err) {
 			free(input);
@@ -988,8 +989,8 @@ skip_freplace_fixup:
 
 static int process_prog(const char *filename, struct bpf_object *obj, struct bpf_program *prog)
 {
+	const char *base_filename = basename(strdupa(filename));
 	const char *prog_name = bpf_program__name(prog);
-	const char *base_filename = basename(filename);
 	char *buf;
 	int buf_sz, log_level;
 	struct verif_stats *stats;
@@ -1056,13 +1057,14 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf
 
 static int process_obj(const char *filename)
 {
+	const char *base_filename = basename(strdupa(filename));
 	struct bpf_object *obj = NULL, *tobj;
 	struct bpf_program *prog, *tprog, *lprog;
 	libbpf_print_fn_t old_libbpf_print_fn;
 	LIBBPF_OPTS(bpf_object_open_opts, opts);
 	int err = 0, prog_cnt = 0;
 
-	if (!should_process_file_prog(basename(filename), NULL)) {
+	if (!should_process_file_prog(base_filename, NULL)) {
 		if (env.verbose)
 			printf("Skipping '%s' due to filters...\n", filename);
 		env.files_skipped++;
@@ -1076,7 +1078,7 @@ static int process_obj(const char *filename)
 	}
 
 	if (!env.quiet && env.out_fmt == RESFMT_TABLE)
-		printf("Processing '%s'...\n", basename(filename));
+		printf("Processing '%s'...\n", base_filename);
 
 	old_libbpf_print_fn = libbpf_set_print(libbpf_print_fn);
 	obj = bpf_object__open_file(filename, &opts);
@@ -1493,7 +1495,7 @@ static int parse_stats_csv(const char *filename, struct stat_specs *specs,
 	while (fgets(line, sizeof(line), f)) {
 		char *input = line, *state = NULL, *next;
 		struct verif_stats *st = NULL;
-		int col = 0;
+		int col = 0, cnt = 0;
 
 		if (!header) {
 			void *tmp;
@@ -1511,7 +1513,7 @@ static int parse_stats_csv(const char *filename, struct stat_specs *specs,
 			*stat_cntp += 1;
 		}
 
-		while ((next = strtok_r(state ? NULL : input, ",\n", &state))) {
+		while ((next = strtok_r(cnt++ ? NULL : input, ",\n", &state))) {
 			if (header) {
 				/* for the first line, set up spec stats */
 				err = parse_stat(next, specs);
diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh
index 65d14f3bbe30..79505d294c44 100755
--- a/tools/testing/selftests/bpf/vmtest.sh
+++ b/tools/testing/selftests/bpf/vmtest.sh
@@ -1,31 +1,47 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-set -u
 set -e
 
-# This script currently only works for x86_64 and s390x, as
-# it is based on the VM image used by the BPF CI, which is
-# available only for these architectures.
-ARCH="$(uname -m)"
-case "${ARCH}" in
+# This script currently only works for the following platforms,
+# as it is based on the VM image used by the BPF CI, which is
+# available only for these architectures. We can also specify
+# the local rootfs image generated by the following script:
+# https://github.com/libbpf/ci/blob/main/rootfs/mkrootfs_debian.sh
+PLATFORM="${PLATFORM:-$(uname -m)}"
+case "${PLATFORM}" in
 s390x)
 	QEMU_BINARY=qemu-system-s390x
 	QEMU_CONSOLE="ttyS1"
-	QEMU_FLAGS=(-smp 2)
+	HOST_FLAGS=(-smp 2 -enable-kvm)
+	CROSS_FLAGS=(-smp 2)
 	BZIMAGE="arch/s390/boot/vmlinux"
+	ARCH="s390"
 	;;
 x86_64)
 	QEMU_BINARY=qemu-system-x86_64
 	QEMU_CONSOLE="ttyS0,115200"
-	QEMU_FLAGS=(-cpu host -smp 8)
+	HOST_FLAGS=(-cpu host -enable-kvm -smp 8)
+	CROSS_FLAGS=(-smp 8)
 	BZIMAGE="arch/x86/boot/bzImage"
+	ARCH="x86"
 	;;
 aarch64)
 	QEMU_BINARY=qemu-system-aarch64
 	QEMU_CONSOLE="ttyAMA0,115200"
-	QEMU_FLAGS=(-M virt,gic-version=3 -cpu host -smp 8)
+	HOST_FLAGS=(-M virt,gic-version=3 -cpu host -enable-kvm -smp 8)
+	CROSS_FLAGS=(-M virt,gic-version=3 -cpu cortex-a76 -smp 8)
 	BZIMAGE="arch/arm64/boot/Image"
+	ARCH="arm64"
+	;;
+riscv64)
+	# required qemu version v7.2.0+
+	QEMU_BINARY=qemu-system-riscv64
+	QEMU_CONSOLE="ttyS0,115200"
+	HOST_FLAGS=(-M virt -cpu host -enable-kvm -smp 8)
+	CROSS_FLAGS=(-M virt -cpu rv64,sscofpmf=true -smp 8)
+	BZIMAGE="arch/riscv/boot/Image"
+	ARCH="riscv"
 	;;
 *)
 	echo "Unsupported architecture"
@@ -34,11 +50,12 @@ aarch64)
 esac
 DEFAULT_COMMAND="./test_progs"
 MOUNT_DIR="mnt"
+LOCAL_ROOTFS_IMAGE=""
 ROOTFS_IMAGE="root.img"
 OUTPUT_DIR="$HOME/.bpf_selftests"
 KCONFIG_REL_PATHS=("tools/testing/selftests/bpf/config"
 	"tools/testing/selftests/bpf/config.vm"
-	"tools/testing/selftests/bpf/config.${ARCH}")
+	"tools/testing/selftests/bpf/config.${PLATFORM}")
 INDEX_URL="https://raw.githubusercontent.com/libbpf/ci/master/INDEX"
 NUM_COMPILE_JOBS="$(nproc)"
 LOG_FILE_BASE="$(date +"bpf_selftests.%Y-%m-%d_%H-%M-%S")"
@@ -58,6 +75,10 @@ tools/testing/selftests/bpf. e.g:
 If no command is specified and a debug shell (-s) is not requested,
 "${DEFAULT_COMMAND}" will be run by default.
 
+Using PLATFORM= and CROSS_COMPILE= options will enable cross platform testing:
+
+  PLATFORM=<platform> CROSS_COMPILE=<toolchain> $0 -- ./test_progs -t test_lsm
+
 If you build your kernel using KBUILD_OUTPUT= or O= options, these
 can be passed as environment variables to the script:
 
@@ -69,6 +90,7 @@ or
 
 Options:
 
+	-l)             Specify the path to the local rootfs image.
 	-i)		Update the rootfs image with a newer version.
 	-d)		Update the output directory (default: ${OUTPUT_DIR})
 	-j)		Number of jobs for compilation, similar to -j in make
@@ -92,24 +114,11 @@ populate_url_map()
 	fi
 }
 
-download()
-{
-	local file="$1"
-
-	if [[ ! -v URLS[$file] ]]; then
-		echo "$file not found" >&2
-		return 1
-	fi
-
-	echo "Downloading $file..." >&2
-	curl -Lsf "${URLS[$file]}" "${@:2}"
-}
-
 newest_rootfs_version()
 {
 	{
 	for file in "${!URLS[@]}"; do
-		if [[ $file =~ ^"${ARCH}"/libbpf-vmtest-rootfs-(.*)\.tar\.zst$ ]]; then
+		if [[ $file =~ ^"${PLATFORM}"/libbpf-vmtest-rootfs-(.*)\.tar\.zst$ ]]; then
 			echo "${BASH_REMATCH[1]}"
 		fi
 	done
@@ -118,16 +127,34 @@ newest_rootfs_version()
 
 download_rootfs()
 {
-	local rootfsversion="$1"
-	local dir="$2"
+	populate_url_map
+
+	local rootfsversion="$(newest_rootfs_version)"
+	local file="${PLATFORM}/libbpf-vmtest-rootfs-$rootfsversion.tar.zst"
+
+	if [[ ! -v URLS[$file] ]]; then
+		echo "$file not found" >&2
+		return 1
+	fi
+
+	echo "Downloading $file..." >&2
+	curl -Lsf "${URLS[$file]}" "${@:2}"
+}
+
+load_rootfs()
+{
+	local dir="$1"
 
 	if ! which zstd &> /dev/null; then
 		echo 'Could not find "zstd" on the system, please install zstd'
 		exit 1
 	fi
 
-	download "${ARCH}/libbpf-vmtest-rootfs-$rootfsversion.tar.zst" |
-		zstd -d | sudo tar -C "$dir" -x
+	if [[ -n "${LOCAL_ROOTFS_IMAGE}" ]]; then
+		cat "${LOCAL_ROOTFS_IMAGE}" | zstd -d | sudo tar -C "$dir" -x
+	else
+		download_rootfs | zstd -d | sudo tar -C "$dir" -x
+	fi
 }
 
 recompile_kernel()
@@ -227,7 +254,7 @@ create_vm_image()
 	mkfs.ext4 -q "${rootfs_img}"
 
 	mount_image
-	download_rootfs "$(newest_rootfs_version)" "${mount_dir}"
+	load_rootfs "${mount_dir}"
 	unmount_image
 }
 
@@ -244,12 +271,17 @@ EOF
 		exit 1
 	fi
 
+	if [[ "${PLATFORM}" != "$(uname -m)" ]]; then
+		QEMU_FLAGS=("${CROSS_FLAGS[@]}")
+	else
+		QEMU_FLAGS=("${HOST_FLAGS[@]}")
+	fi
+
 	${QEMU_BINARY} \
 		-nodefaults \
 		-display none \
 		-serial mon:stdio \
 		"${QEMU_FLAGS[@]}" \
-		-enable-kvm \
 		-m 4G \
 		-drive file="${rootfs_img}",format=raw,index=1,media=disk,if=virtio,cache=none \
 		-kernel "${kernel_bzimage}" \
@@ -341,8 +373,11 @@ main()
 	local exit_command="poweroff -f"
 	local debug_shell="no"
 
-	while getopts ':hskid:j:' opt; do
+	while getopts ':hskl:id:j:' opt; do
 		case ${opt} in
+		l)
+			LOCAL_ROOTFS_IMAGE="$OPTARG"
+			;;
 		i)
 			update_image="yes"
 			;;
@@ -377,6 +412,11 @@ main()
 
 	trap 'catch "$?"' EXIT
 
+	if [[ "${PLATFORM}" != "$(uname -m)" ]] && [[ -z "${CROSS_COMPILE}" ]]; then
+		echo "Cross-platform testing needs to specify CROSS_COMPILE"
+		exit 1
+	fi
+
 	if [[ $# -eq 0  && "${debug_shell}" == "no" ]]; then
 		echo "No command specified, will run ${DEFAULT_COMMAND} in the vm"
 	else
@@ -384,7 +424,8 @@ main()
 	fi
 
 	local kconfig_file="${OUTPUT_DIR}/latest.config"
-	local make_command="make -j ${NUM_COMPILE_JOBS} KCONFIG_CONFIG=${kconfig_file}"
+	local make_command="make ARCH=${ARCH} CROSS_COMPILE=${CROSS_COMPILE} \
+			    -j ${NUM_COMPILE_JOBS} KCONFIG_CONFIG=${kconfig_file}"
 
 	# Figure out where the kernel is being built.
 	# O takes precedence over KBUILD_OUTPUT.
@@ -402,8 +443,6 @@ main()
 		make_command="${make_command} KBUILD_OUTPUT=${KBUILD_OUTPUT}"
 	fi
 
-	populate_url_map
-
 	local rootfs_img="${OUTPUT_DIR}/${ROOTFS_IMAGE}"
 	local mount_dir="${OUTPUT_DIR}/${MOUNT_DIR}"
 
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 1ee0ef114f9d..11f047b8af75 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -90,6 +90,7 @@
 #include <signal.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <libgen.h>
 #include <string.h>
 #include <stddef.h>
 #include <sys/mman.h>