Merge tag 'bpf-next-7.0' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Pull bpf updates from Alexei Starovoitov:

 - Support associating BPF program with struct_ops (Amery Hung)

 - Switch BPF local storage to rqspinlock and remove recursion detection
   counters which were causing false positives (Amery Hung)

 - Fix live registers marking for indirect jumps (Anton Protopopov)

 - Introduce execution context detection BPF helpers (Changwoo Min)

 - Improve verifier precision for 32bit sign extension pattern
   (Cupertino Miranda)

 - Optimize BTF type lookup by sorting vmlinux BTF and doing binary
   search (Donglin Peng)

 - Allow states pruning for misc/invalid slots in iterator loops (Eduard
   Zingerman)

 - In preparation for ASAN support in BPF arenas teach libbpf to move
   global BPF variables to the end of the region and enable arena kfuncs
   while holding locks (Emil Tsalapatis)

 - Introduce support for implicit arguments in kfuncs and migrate a
   number of them to new API. This is a prerequisite for cgroup
   sub-schedulers in sched-ext (Ihor Solodrai)

 - Fix incorrect copied_seq calculation in sockmap (Jiayuan Chen)

 - Fix ORC stack unwind from kprobe_multi (Jiri Olsa)

 - Speed up fentry attach by using single ftrace direct ops in BPF
   trampolines (Jiri Olsa)

 - Require frozen map for calculating map hash (KP Singh)

 - Fix lock entry creation in TAS fallback in rqspinlock (Kumar
   Kartikeya Dwivedi)

 - Allow user space to select cpu in lookup/update operations on per-cpu
   array and hash maps (Leon Hwang)

 - Make kfuncs return trusted pointers by default (Matt Bobrowski)

 - Introduce "fsession" support where single BPF program is executed
   upon entry and exit from traced kernel function (Menglong Dong)

 - Allow bpf_timer and bpf_wq use in all programs types (Mykyta
   Yatsenko, Andrii Nakryiko, Kumar Kartikeya Dwivedi, Alexei
   Starovoitov)

 - Make KF_TRUSTED_ARGS the default for all kfuncs and clean up their
   definition across the tree (Puranjay Mohan)

 - Allow BPF arena calls from non-sleepable context (Puranjay Mohan)

 - Improve register id comparison logic in the verifier and extend
   linked registers with negative offsets (Puranjay Mohan)

 - In preparation for BPF-OOM introduce kfuncs to access memcg events
   (Roman Gushchin)

 - Use CFI compatible destructor kfunc type (Sami Tolvanen)

 - Add bitwise tracking for BPF_END in the verifier (Tianci Cao)

 - Add range tracking for BPF_DIV and BPF_MOD in the verifier (Yazhou
   Tang)

 - Make BPF selftests work with 64k page size (Yonghong Song)

* tag 'bpf-next-7.0' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (268 commits)
  selftests/bpf: Fix outdated test on storage->smap
  selftests/bpf: Choose another percpu variable in bpf for btf_dump test
  selftests/bpf: Remove test_task_storage_map_stress_lookup
  selftests/bpf: Update task_local_storage/task_storage_nodeadlock test
  selftests/bpf: Update task_local_storage/recursion test
  selftests/bpf: Update sk_storage_omem_uncharge test
  bpf: Switch to bpf_selem_unlink_nofail in bpf_local_storage_{map_free, destroy}
  bpf: Support lockless unlink when freeing map or local storage
  bpf: Prepare for bpf_selem_unlink_nofail()
  bpf: Remove unused percpu counter from bpf_local_storage_map_free
  bpf: Remove cgroup local storage percpu counter
  bpf: Remove task local storage percpu counter
  bpf: Change local_storage->lock and b->lock to rqspinlock
  bpf: Convert bpf_selem_unlink to failable
  bpf: Convert bpf_selem_link_map to failable
  bpf: Convert bpf_selem_unlink_map to failable
  bpf: Select bpf_local_storage_map_bucket based on bpf_local_storage
  selftests/xsk: fix number of Tx frags in invalid packet
  selftests/xsk: properly handle batch ending in the middle of a packet
  bpf: Prevent reentrance into call_rcu_tasks_trace()
  ...

139 files changed, 7141 insertions, 1027 deletions

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 19c1638e312a..a3ea98211ea6 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -23,7 +23,6 @@ test_tcpnotify_user
 test_libbpf
 xdping
 test_cpp
-test_progs_verification_cert
 *.d
 *.subskel.h
 *.skel.h
@@ -45,3 +44,6 @@ xdp_synproxy
 xdp_hw_metadata
 xdp_features
 verification_cert.h
+*.BTF
+*.BTF_ids
+*.BTF.base
diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x
index a17baf8c6fd7..f7e1e5f5511c 100644
--- a/tools/testing/selftests/bpf/DENYLIST.s390x
+++ b/tools/testing/selftests/bpf/DENYLIST.s390x
@@ -1,4 +1,5 @@
 # TEMPORARY
 # Alphabetical order
+exe_ctx                                  # execution context check (e.g., hardirq, softirq, etc)
 get_stack_raw_tp                         # user_stack corrupted user stack                                             (no backchain userspace)
 stacktrace_build_id                      # compare_map_keys stackid_hmap vs. stackmap err -2 errno 2                   (?)
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 4aa60e83ff19..c6bf4dfb1495 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -4,6 +4,7 @@ include ../../../scripts/Makefile.arch
 include ../../../scripts/Makefile.include
 
 CXX ?= $(CROSS_COMPILE)g++
+OBJCOPY ?= $(CROSS_COMPILE)objcopy
 
 CURDIR := $(abspath .)
 TOOLSDIR := $(abspath ../../..)
@@ -107,8 +108,6 @@ TEST_PROGS := test_kmod.sh \
 	test_xdping.sh \
 	test_bpftool_build.sh \
 	test_bpftool.sh \
-	test_bpftool_map.sh \
-	test_bpftool_metadata.sh \
 	test_doc_build.sh \
 	test_xsk.sh \
 	test_xdp_features.sh
@@ -643,6 +642,9 @@ $(TRUNNER_TESTS_HDR): $(TRUNNER_TESTS_DIR)/*.c
 		 ) > $$@)
 endif
 
+$(TRUNNER_OUTPUT)/resolve_btfids.test.o: $(RESOLVE_BTFIDS) $(TRUNNER_OUTPUT)/btf_data.bpf.o
+$(TRUNNER_OUTPUT)/resolve_btfids.test.o: private TEST_NEEDS_BTFIDS = 1
+
 # compile individual test files
 # Note: we cd into output directory to ensure embedded BPF object is found
 $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o:			\
@@ -650,6 +652,10 @@ $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o:			\
 		      | $(TRUNNER_OUTPUT)/%.test.d
 	$$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@)
 	$(Q)cd $$(@D) && $$(CC) -I. $$(CFLAGS) -MMD -MT $$@ -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F)
+	$$(if $$(TEST_NEEDS_BTFIDS),						\
+		$$(call msg,BTFIDS,$(TRUNNER_BINARY),$$@)			\
+		$(RESOLVE_BTFIDS) --btf $(TRUNNER_OUTPUT)/btf_data.bpf.o $$@;	\
+		$(RESOLVE_BTFIDS) --patch_btfids $$@.BTF_ids $$@)
 
 $(TRUNNER_TEST_OBJS:.o=.d): $(TRUNNER_OUTPUT)/%.test.d:			\
 			    $(TRUNNER_TESTS_DIR)/%.c			\
@@ -695,13 +701,11 @@ $(OUTPUT)/$(TRUNNER_BINARY): | $(TRUNNER_BPF_OBJS)
 $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS)			\
 			     $(TRUNNER_EXTRA_OBJS) $$(BPFOBJ)		\
 			     $(TRUNNER_LIB_OBJS)			\
-			     $(RESOLVE_BTFIDS)				\
 			     $(TRUNNER_BPFTOOL)				\
 			     $(OUTPUT)/veristat				\
 			     | $(TRUNNER_BINARY)-extras
 	$$(call msg,BINARY,,$$@)
 	$(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) $$(LLVM_LDLIBS) $$(LDFLAGS) $$(LLVM_LDFLAGS) -o $$@
-	$(Q)$(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
 
@@ -716,9 +720,12 @@ $(VERIFICATION_CERT) $(PRIVATE_KEY): $(VERIFY_SIG_SETUP)
 	$(Q)mkdir -p $(BUILD_DIR)
 	$(Q)$(VERIFY_SIG_SETUP) genkey $(BUILD_DIR)
 
+# Generates a header with C array declaration, containing test_progs_verification_cert bytes
 $(VERIFY_SIG_HDR): $(VERIFICATION_CERT)
-	$(Q)ln -fs $< test_progs_verification_cert && \
-	xxd -i test_progs_verification_cert > $@
+	$(Q)(echo "unsigned char test_progs_verification_cert[] = {"; \
+	 hexdump -v -e '12/1 "  0x%02x," "\n"' $< | sed 's/0x  ,//g; $$s/,$$//'; \
+	 echo "};"; \
+	 echo "unsigned int test_progs_verification_cert_len = $$(wc -c < $<);") > $@
 
 # Define test_progs test runner.
 TRUNNER_TESTS_DIR := prog_tests
@@ -741,7 +748,8 @@ TRUNNER_EXTRA_SOURCES := test_progs.c		\
 			 json_writer.c 		\
 			 $(VERIFY_SIG_HDR)		\
 			 flow_dissector_load.h	\
-			 ip_check_defrag_frags.h
+			 ip_check_defrag_frags.h	\
+			 bpftool_helpers.c
 TRUNNER_LIB_SOURCES := find_bit.c
 TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read				\
 		       $(OUTPUT)/liburandom_read.so			\
@@ -890,10 +898,10 @@ EXTRA_CLEAN := $(SCRATCH_DIR) $(HOST_SCRATCH_DIR)			\
 	prog_tests/tests.h map_tests/tests.h verifier/tests.h		\
 	feature bpftool $(TEST_KMOD_TARGETS)				\
 	$(addprefix $(OUTPUT)/,*.o *.d *.skel.h *.lskel.h *.subskel.h	\
+			       *.BTF *.BTF_ids *.BTF.base		\
 			       no_alu32 cpuv4 bpf_gcc			\
 			       liburandom_read.so)			\
-	$(OUTPUT)/FEATURE-DUMP.selftests				\
-	test_progs_verification_cert
+	$(OUTPUT)/FEATURE-DUMP.selftests
 
 .PHONY: docs docs-clean
 
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index bd29bb2e6cb5..8368bd3a0665 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -265,6 +265,7 @@ static const struct argp_option opts[] = {
 	{ "verbose", 'v', NULL, 0, "Verbose debug output"},
 	{ "affinity", 'a', NULL, 0, "Set consumer/producer thread affinity"},
 	{ "quiet", 'q', NULL, 0, "Be more quiet"},
+	{ "stacktrace", 's', NULL, 0, "Get stack trace"},
 	{ "prod-affinity", ARG_PROD_AFFINITY_SET, "CPUSET", 0,
 	  "Set of CPUs for producer threads; implies --affinity"},
 	{ "cons-affinity", ARG_CONS_AFFINITY_SET, "CPUSET", 0,
@@ -350,6 +351,9 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 	case 'q':
 		env.quiet = true;
 		break;
+	case 's':
+		env.stacktrace = true;
+		break;
 	case ARG_PROD_AFFINITY_SET:
 		env.affinity = true;
 		if (parse_num_list(arg, &env.prod_cpus.cpus,
diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h
index bea323820ffb..7cf21936e7ed 100644
--- a/tools/testing/selftests/bpf/bench.h
+++ b/tools/testing/selftests/bpf/bench.h
@@ -26,6 +26,7 @@ struct env {
 	bool list;
 	bool affinity;
 	bool quiet;
+	bool stacktrace;
 	int consumer_cnt;
 	int producer_cnt;
 	int nr_cpus;
diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
index 34018fc3927f..aeec9edd3851 100644
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -146,6 +146,7 @@ static void setup_ctx(void)
 	bpf_program__set_autoload(ctx.skel->progs.trigger_driver, true);
 
 	ctx.skel->rodata->batch_iters = args.batch_iters;
+	ctx.skel->rodata->stacktrace = env.stacktrace;
 }
 
 static void load_ctx(void)
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh
index 83e05e837871..123b7feb6935 100755
--- a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh
+++ b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh
@@ -49,6 +49,11 @@ for b in 1 2 3 4 8 12 16 20 24 28 32 36 40 44 48 52; do
 	summarize "rb-libbpf nr_prod $b" "$($RUN_RB_BENCH -p$b --rb-batch-cnt 50 rb-libbpf)"
 done
 
+header "Perfbuf, multi-producer"
+for b in 1 2 3 4 8 12 16 20 24 28 32 36 40 44 48 52; do
+	summarize "pb-libbpf nr_prod $b" "$($RUN_RB_BENCH -p$b --rb-batch-cnt 50 --rb-sample-rate 50 pb-libbpf)"
+done
+
 header "Ringbuf, multi-producer contention in overwrite mode, no consumer"
 for b in 1 2 3 4 8 12 16 20 24 28 32 36 40 44 48 52; do
 	summarize "rb-prod nr_prod $b" "$($RUN_BENCH -p$b --rb-batch-cnt 50 --rb-overwrite --rb-bench-producer rb-libbpf)"
diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 2cd9165c7348..4b7210c318dd 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -580,11 +580,6 @@ extern void bpf_iter_css_destroy(struct bpf_iter_css *it) __weak __ksym;
 
 extern int bpf_wq_init(struct bpf_wq *wq, void *p__map, unsigned int flags) __weak __ksym;
 extern int bpf_wq_start(struct bpf_wq *wq, unsigned int flags) __weak __ksym;
-extern int bpf_wq_set_callback_impl(struct bpf_wq *wq,
-		int (callback_fn)(void *map, int *key, void *value),
-		unsigned int flags__k, void *aux__ign) __ksym;
-#define bpf_wq_set_callback(timer, cb, flags) \
-	bpf_wq_set_callback_impl(timer, cb, flags, NULL)
 
 struct bpf_iter_kmem_cache;
 extern int bpf_iter_kmem_cache_new(struct bpf_iter_kmem_cache *it) __weak __ksym;
@@ -615,9 +610,17 @@ extern int bpf_cgroup_read_xattr(struct cgroup *cgroup, const char *name__str,
 #define HARDIRQ_MASK	(__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
 #define NMI_MASK	(__IRQ_MASK(NMI_BITS)     << NMI_SHIFT)
 
+#define SOFTIRQ_OFFSET	(1UL << SOFTIRQ_SHIFT)
+
 extern bool CONFIG_PREEMPT_RT __kconfig __weak;
 #ifdef bpf_target_x86
-extern const int __preempt_count __ksym;
+extern const int __preempt_count __ksym __weak;
+
+struct pcpu_hot___local {
+	int preempt_count;
+} __attribute__((preserve_access_index));
+
+extern struct pcpu_hot___local pcpu_hot __ksym __weak;
 #endif
 
 struct task_struct___preempt_rt {
@@ -627,7 +630,19 @@ struct task_struct___preempt_rt {
 static inline int get_preempt_count(void)
 {
 #if defined(bpf_target_x86)
-	return *(int *) bpf_this_cpu_ptr(&__preempt_count);
+	/* By default, read the per-CPU __preempt_count. */
+	if (bpf_ksym_exists(&__preempt_count))
+		return *(int *) bpf_this_cpu_ptr(&__preempt_count);
+
+	/*
+	 * If __preempt_count does not exist, try to read preempt_count under
+	 * struct pcpu_hot. Between v6.1 and v6.14 -- more specifically,
+	 * [64701838bf057, 46e8fff6d45fe), preempt_count had been managed
+	 * under struct pcpu_hot.
+	 */
+	if (bpf_core_field_exists(pcpu_hot.preempt_count))
+		return ((struct pcpu_hot___local *)
+			bpf_this_cpu_ptr(&pcpu_hot))->preempt_count;
 #elif defined(bpf_target_arm64)
 	return bpf_get_current_task_btf()->thread_info.preempt.count;
 #endif
@@ -653,4 +668,60 @@ static inline int bpf_in_interrupt(void)
 	       (tsk->softirq_disable_cnt & SOFTIRQ_MASK);
 }
 
+/* Description
+ *	Report whether it is in NMI context. Only works on the following archs:
+ *	* x86
+ *	* arm64
+ */
+static inline int bpf_in_nmi(void)
+{
+	return get_preempt_count() & NMI_MASK;
+}
+
+/* Description
+ *	Report whether it is in hard IRQ context. Only works on the following archs:
+ *	* x86
+ *	* arm64
+ */
+static inline int bpf_in_hardirq(void)
+{
+	return get_preempt_count() & HARDIRQ_MASK;
+}
+
+/* Description
+ *	Report whether it is in softirq context. Only works on the following archs:
+ *	* x86
+ *	* arm64
+ */
+static inline int bpf_in_serving_softirq(void)
+{
+	struct task_struct___preempt_rt *tsk;
+	int pcnt;
+
+	pcnt = get_preempt_count();
+	if (!CONFIG_PREEMPT_RT)
+		return (pcnt & SOFTIRQ_MASK) & SOFTIRQ_OFFSET;
+
+	tsk = (void *) bpf_get_current_task_btf();
+	return (tsk->softirq_disable_cnt & SOFTIRQ_MASK) & SOFTIRQ_OFFSET;
+}
+
+/* Description
+ *	Report whether it is in task context. Only works on the following archs:
+ *	* x86
+ *	* arm64
+ */
+static inline int bpf_in_task(void)
+{
+	struct task_struct___preempt_rt *tsk;
+	int pcnt;
+
+	pcnt = get_preempt_count();
+	if (!CONFIG_PREEMPT_RT)
+		return !(pcnt & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET));
+
+	tsk = (void *) bpf_get_current_task_btf();
+	return !((pcnt & (NMI_MASK | HARDIRQ_MASK)) |
+		 ((tsk->softirq_disable_cnt & SOFTIRQ_MASK) & SOFTIRQ_OFFSET));
+}
 #endif
diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h
index e0189254bb6e..7dad01439391 100644
--- a/tools/testing/selftests/bpf/bpf_kfuncs.h
+++ b/tools/testing/selftests/bpf/bpf_kfuncs.h
@@ -79,9 +79,6 @@ extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr,
 				      struct bpf_dynptr *sig_ptr,
 				      struct bpf_key *trusted_keyring) __ksym;
 
-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
diff --git a/tools/testing/selftests/bpf/bpftool_helpers.c b/tools/testing/selftests/bpf/bpftool_helpers.c
new file mode 100644
index 000000000000..a5824945a4a5
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpftool_helpers.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "bpftool_helpers.h"
+#include <unistd.h>
+#include <string.h>
+#include <stdbool.h>
+
+#define BPFTOOL_PATH_MAX_LEN		64
+#define BPFTOOL_FULL_CMD_MAX_LEN	512
+
+#define BPFTOOL_DEFAULT_PATH		"tools/sbin/bpftool"
+
+static int detect_bpftool_path(char *buffer)
+{
+	char tmp[BPFTOOL_PATH_MAX_LEN];
+
+	/* Check default bpftool location (will work if we are running the
+	 * default flavor of test_progs)
+	 */
+	snprintf(tmp, BPFTOOL_PATH_MAX_LEN, "./%s", BPFTOOL_DEFAULT_PATH);
+	if (access(tmp, X_OK) == 0) {
+		strncpy(buffer, tmp, BPFTOOL_PATH_MAX_LEN);
+		return 0;
+	}
+
+	/* Check alternate bpftool location (will work if we are running a
+	 * specific flavor of test_progs, e.g. cpuv4 or no_alu32)
+	 */
+	snprintf(tmp, BPFTOOL_PATH_MAX_LEN, "../%s", BPFTOOL_DEFAULT_PATH);
+	if (access(tmp, X_OK) == 0) {
+		strncpy(buffer, tmp, BPFTOOL_PATH_MAX_LEN);
+		return 0;
+	}
+
+	/* Failed to find bpftool binary */
+	return 1;
+}
+
+static int run_command(char *args, char *output_buf, size_t output_max_len)
+{
+	static char bpftool_path[BPFTOOL_PATH_MAX_LEN] = {0};
+	bool suppress_output = !(output_buf && output_max_len);
+	char command[BPFTOOL_FULL_CMD_MAX_LEN];
+	FILE *f;
+	int ret;
+
+	/* Detect and cache bpftool binary location */
+	if (bpftool_path[0] == 0 && detect_bpftool_path(bpftool_path))
+		return 1;
+
+	ret = snprintf(command, BPFTOOL_FULL_CMD_MAX_LEN, "%s %s%s",
+		       bpftool_path, args,
+		       suppress_output ? " > /dev/null 2>&1" : "");
+
+	f = popen(command, "r");
+	if (!f)
+		return 1;
+
+	if (!suppress_output)
+		fread(output_buf, 1, output_max_len, f);
+	ret = pclose(f);
+
+	return ret;
+}
+
+int run_bpftool_command(char *args)
+{
+	return run_command(args, NULL, 0);
+}
+
+int get_bpftool_command_output(char *args, char *output_buf, size_t output_max_len)
+{
+	return run_command(args, output_buf, output_max_len);
+}
+
diff --git a/tools/testing/selftests/bpf/bpftool_helpers.h b/tools/testing/selftests/bpf/bpftool_helpers.h
new file mode 100644
index 000000000000..dec1ba201410
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpftool_helpers.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#pragma once
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdbool.h>
+
+#define MAX_BPFTOOL_CMD_LEN	(256)
+
+int run_bpftool_command(char *args);
+int get_bpftool_command_output(char *args, char *output_buf, size_t output_max_len);
diff --git a/tools/testing/selftests/bpf/cgroup_iter_memcg.h b/tools/testing/selftests/bpf/cgroup_iter_memcg.h
new file mode 100644
index 000000000000..3f59b127943b
--- /dev/null
+++ b/tools/testing/selftests/bpf/cgroup_iter_memcg.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#ifndef __CGROUP_ITER_MEMCG_H
+#define __CGROUP_ITER_MEMCG_H
+
+struct memcg_query {
+	/* some node_stat_item's */
+	unsigned long nr_anon_mapped;
+	unsigned long nr_shmem;
+	unsigned long nr_file_pages;
+	unsigned long nr_file_mapped;
+	/* some memcg_stat_item */
+	unsigned long memcg_kmem;
+	/* some vm_event_item */
+	unsigned long pgfault;
+};
+
+#endif /* __CGROUP_ITER_MEMCG_H */
diff --git a/tools/testing/selftests/bpf/map_tests/task_storage_map.c b/tools/testing/selftests/bpf/map_tests/task_storage_map.c
deleted file mode 100644
index a4121d2248ac..000000000000
--- a/tools/testing/selftests/bpf/map_tests/task_storage_map.c
+++ /dev/null
@@ -1,128 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2022. Huawei Technologies Co., Ltd */
-#define _GNU_SOURCE
-#include <sched.h>
-#include <unistd.h>
-#include <stdlib.h>
-#include <stdbool.h>
-#include <errno.h>
-#include <string.h>
-#include <pthread.h>
-
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include "bpf_util.h"
-#include "test_maps.h"
-#include "task_local_storage_helpers.h"
-#include "read_bpf_task_storage_busy.skel.h"
-
-struct lookup_ctx {
-	bool start;
-	bool stop;
-	int pid_fd;
-	int map_fd;
-	int loop;
-};
-
-static void *lookup_fn(void *arg)
-{
-	struct lookup_ctx *ctx = arg;
-	long value;
-	int i = 0;
-
-	while (!ctx->start)
-		usleep(1);
-
-	while (!ctx->stop && i++ < ctx->loop)
-		bpf_map_lookup_elem(ctx->map_fd, &ctx->pid_fd, &value);
-	return NULL;
-}
-
-static void abort_lookup(struct lookup_ctx *ctx, pthread_t *tids, unsigned int nr)
-{
-	unsigned int i;
-
-	ctx->stop = true;
-	ctx->start = true;
-	for (i = 0; i < nr; i++)
-		pthread_join(tids[i], NULL);
-}
-
-void test_task_storage_map_stress_lookup(void)
-{
-#define MAX_NR_THREAD 4096
-	unsigned int i, nr = 256, loop = 8192, cpu = 0;
-	struct read_bpf_task_storage_busy *skel;
-	pthread_t tids[MAX_NR_THREAD];
-	struct lookup_ctx ctx;
-	cpu_set_t old, new;
-	const char *cfg;
-	int err;
-
-	cfg = getenv("TASK_STORAGE_MAP_NR_THREAD");
-	if (cfg) {
-		nr = atoi(cfg);
-		if (nr > MAX_NR_THREAD)
-			nr = MAX_NR_THREAD;
-	}
-	cfg = getenv("TASK_STORAGE_MAP_NR_LOOP");
-	if (cfg)
-		loop = atoi(cfg);
-	cfg = getenv("TASK_STORAGE_MAP_PIN_CPU");
-	if (cfg)
-		cpu = atoi(cfg);
-
-	skel = read_bpf_task_storage_busy__open_and_load();
-	err = libbpf_get_error(skel);
-	CHECK(err, "open_and_load", "error %d\n", err);
-
-	/* Only for a fully preemptible kernel */
-	if (!skel->kconfig->CONFIG_PREEMPTION) {
-		printf("%s SKIP (no CONFIG_PREEMPTION)\n", __func__);
-		read_bpf_task_storage_busy__destroy(skel);
-		skips++;
-		return;
-	}
-
-	/* Save the old affinity setting */
-	sched_getaffinity(getpid(), sizeof(old), &old);
-
-	/* Pinned on a specific CPU */
-	CPU_ZERO(&new);
-	CPU_SET(cpu, &new);
-	sched_setaffinity(getpid(), sizeof(new), &new);
-
-	ctx.start = false;
-	ctx.stop = false;
-	ctx.pid_fd = sys_pidfd_open(getpid(), 0);
-	ctx.map_fd = bpf_map__fd(skel->maps.task);
-	ctx.loop = loop;
-	for (i = 0; i < nr; i++) {
-		err = pthread_create(&tids[i], NULL, lookup_fn, &ctx);
-		if (err) {
-			abort_lookup(&ctx, tids, i);
-			CHECK(err, "pthread_create", "error %d\n", err);
-			goto out;
-		}
-	}
-
-	ctx.start = true;
-	for (i = 0; i < nr; i++)
-		pthread_join(tids[i], NULL);
-
-	skel->bss->pid = getpid();
-	err = read_bpf_task_storage_busy__attach(skel);
-	CHECK(err, "attach", "error %d\n", err);
-
-	/* Trigger program */
-	sys_gettid();
-	skel->bss->pid = 0;
-
-	CHECK(skel->bss->busy != 0, "bad bpf_task_storage_busy", "got %d\n", skel->bss->busy);
-out:
-	read_bpf_task_storage_busy__destroy(skel);
-	/* Restore affinity setting */
-	sched_setaffinity(getpid(), sizeof(old), &old);
-	printf("%s:PASS\n", __func__);
-}
diff --git a/tools/testing/selftests/bpf/prog_tests/arena_list.c b/tools/testing/selftests/bpf/prog_tests/arena_list.c
index d15867cddde0..4f2866a615ce 100644
--- a/tools/testing/selftests/bpf/prog_tests/arena_list.c
+++ b/tools/testing/selftests/bpf/prog_tests/arena_list.c
@@ -27,17 +27,23 @@ static int list_sum(struct arena_list_head *head)
 	return sum;
 }
 
-static void test_arena_list_add_del(int cnt)
+static void test_arena_list_add_del(int cnt, bool nonsleepable)
 {
 	LIBBPF_OPTS(bpf_test_run_opts, opts);
 	struct arena_list *skel;
 	int expected_sum = (u64)cnt * (cnt - 1) / 2;
 	int ret, sum;
 
-	skel = arena_list__open_and_load();
-	if (!ASSERT_OK_PTR(skel, "arena_list__open_and_load"))
+	skel = arena_list__open();
+	if (!ASSERT_OK_PTR(skel, "arena_list__open"))
 		return;
 
+	skel->rodata->nonsleepable = nonsleepable;
+
+	ret = arena_list__load(skel);
+	if (!ASSERT_OK(ret, "arena_list__load"))
+		goto out;
+
 	skel->bss->cnt = cnt;
 	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.arena_list_add), &opts);
 	ASSERT_OK(ret, "ret_add");
@@ -65,7 +71,11 @@ out:
 void test_arena_list(void)
 {
 	if (test__start_subtest("arena_list_1"))
-		test_arena_list_add_del(1);
+		test_arena_list_add_del(1, false);
 	if (test__start_subtest("arena_list_1000"))
-		test_arena_list_add_del(1000);
+		test_arena_list_add_del(1000, false);
+	if (test__start_subtest("arena_list_1_nonsleepable"))
+		test_arena_list_add_del(1, true);
+	if (test__start_subtest("arena_list_1000_nonsleepable"))
+		test_arena_list_add_del(1000, true);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_gotox.c b/tools/testing/selftests/bpf/prog_tests/bpf_gotox.c
index d138cc7b1bda..75b0cf2467ab 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_gotox.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_gotox.c
@@ -240,6 +240,208 @@ static void check_nonstatic_global_other_sec(struct bpf_gotox *skel)
 	bpf_link__destroy(link);
 }
 
+/*
+ * The following subtests do not use skeleton rather than to check
+ * if the test should be skipped.
+ */
+
+static int create_jt_map(__u32 max_entries)
+{
+	const char *map_name = "jt";
+	__u32 key_size = 4;
+	__u32 value_size = sizeof(struct bpf_insn_array_value);
+
+	return bpf_map_create(BPF_MAP_TYPE_INSN_ARRAY, map_name,
+			      key_size, value_size, max_entries, NULL);
+}
+
+static int prog_load(struct bpf_insn *insns, __u32 insn_cnt)
+{
+	return bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL);
+}
+
+static int __check_ldimm64_off_prog_load(__u32 max_entries, __u32 off)
+{
+	struct bpf_insn insns[] = {
+		BPF_LD_IMM64_RAW(BPF_REG_1, BPF_PSEUDO_MAP_VALUE, 0),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int map_fd, ret;
+
+	map_fd = create_jt_map(max_entries);
+	if (!ASSERT_GE(map_fd, 0, "create_jt_map"))
+		return -1;
+	if (!ASSERT_EQ(bpf_map_freeze(map_fd), 0, "bpf_map_freeze")) {
+		close(map_fd);
+		return -1;
+	}
+
+	insns[0].imm = map_fd;
+	insns[1].imm = off;
+
+	ret = prog_load(insns, ARRAY_SIZE(insns));
+	close(map_fd);
+	return ret;
+}
+
+/*
+ * Check that loads from an instruction array map are only allowed with offsets
+ * which are multiples of 8 and do not point to outside of the map.
+ */
+static void check_ldimm64_off_load(struct bpf_gotox *skel __always_unused)
+{
+	const __u32 max_entries = 10;
+	int prog_fd;
+	__u32 off;
+
+	for (off = 0; off < max_entries; off++) {
+		prog_fd = __check_ldimm64_off_prog_load(max_entries, off * 8);
+		if (!ASSERT_GE(prog_fd, 0, "__check_ldimm64_off_prog_load"))
+			return;
+		close(prog_fd);
+	}
+
+	prog_fd = __check_ldimm64_off_prog_load(max_entries, 7 /* not a multiple of 8 */);
+	if (!ASSERT_EQ(prog_fd, -EACCES, "__check_ldimm64_off_prog_load: should be -EACCES")) {
+		close(prog_fd);
+		return;
+	}
+
+	prog_fd = __check_ldimm64_off_prog_load(max_entries, max_entries * 8 /* too large */);
+	if (!ASSERT_EQ(prog_fd, -EACCES, "__check_ldimm64_off_prog_load: should be -EACCES")) {
+		close(prog_fd);
+		return;
+	}
+}
+
+static int __check_ldimm64_gotox_prog_load(struct bpf_insn *insns,
+					   __u32 insn_cnt,
+					   __u32 off1, __u32 off2)
+{
+	const __u32 values[] = {5, 7, 9, 11, 13, 15};
+	const __u32 max_entries = ARRAY_SIZE(values);
+	struct bpf_insn_array_value val = {};
+	int map_fd, ret, i;
+
+	map_fd = create_jt_map(max_entries);
+	if (!ASSERT_GE(map_fd, 0, "create_jt_map"))
+		return -1;
+
+	for (i = 0; i < max_entries; i++) {
+		val.orig_off = values[i];
+		if (!ASSERT_EQ(bpf_map_update_elem(map_fd, &i, &val, 0), 0,
+			       "bpf_map_update_elem")) {
+			close(map_fd);
+			return -1;
+		}
+	}
+
+	if (!ASSERT_EQ(bpf_map_freeze(map_fd), 0, "bpf_map_freeze")) {
+		close(map_fd);
+		return -1;
+	}
+
+	/* r1 = &map + offset1 */
+	insns[0].imm = map_fd;
+	insns[1].imm = off1;
+
+	/* r1 += off2 */
+	insns[2].imm = off2;
+
+	ret = prog_load(insns, insn_cnt);
+	close(map_fd);
+	return ret;
+}
+
+static void reject_offsets(struct bpf_insn *insns, __u32 insn_cnt, __u32 off1, __u32 off2)
+{
+	int prog_fd;
+
+	prog_fd = __check_ldimm64_gotox_prog_load(insns, insn_cnt, off1, off2);
+	if (!ASSERT_EQ(prog_fd, -EACCES, "__check_ldimm64_gotox_prog_load"))
+		close(prog_fd);
+}
+
+/*
+ * Verify a bit more complex programs which include indirect jumps
+ * and with jump tables loaded with a non-zero offset
+ */
+static void check_ldimm64_off_gotox(struct bpf_gotox *skel __always_unused)
+{
+	struct bpf_insn insns[] = {
+		/*
+		 * The following instructions perform an indirect jump to
+		 * labels below. Thus valid offsets in the map are {0,...,5}.
+		 * The program rewrites the offsets in the instructions below:
+		 *     r1 = &map + offset1
+		 *     r1 += offset2
+		 *     r1 = *r1
+		 *     gotox r1
+		 */
+		BPF_LD_IMM64_RAW(BPF_REG_1, BPF_PSEUDO_MAP_VALUE, 0),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0),
+		BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_1, 0, 0, 0),
+
+		/* case 0: */
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+		/* case 1: */
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+		/* case 2: */
+		BPF_MOV64_IMM(BPF_REG_0, 2),
+		BPF_EXIT_INSN(),
+		/* case 3: */
+		BPF_MOV64_IMM(BPF_REG_0, 3),
+		BPF_EXIT_INSN(),
+		/* case 4: */
+		BPF_MOV64_IMM(BPF_REG_0, 4),
+		BPF_EXIT_INSN(),
+		/* default: */
+		BPF_MOV64_IMM(BPF_REG_0, 5),
+		BPF_EXIT_INSN(),
+	};
+	int prog_fd, err;
+	__u32 off1, off2;
+
+	/* allow all combinations off1 + off2 < 6 */
+	for (off1 = 0; off1 < 6; off1++) {
+		for (off2 = 0; off1 + off2 < 6; off2++) {
+			LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+			prog_fd = __check_ldimm64_gotox_prog_load(insns, ARRAY_SIZE(insns),
+								  off1 * 8, off2 * 8);
+			if (!ASSERT_GE(prog_fd, 0, "__check_ldimm64_gotox_prog_load"))
+				return;
+
+			err = bpf_prog_test_run_opts(prog_fd, &topts);
+			if (!ASSERT_OK(err, "test_run_opts err")) {
+				close(prog_fd);
+				return;
+			}
+
+			if (!ASSERT_EQ(topts.retval, off1 + off2, "test_run_opts retval")) {
+				close(prog_fd);
+				return;
+			}
+
+			close(prog_fd);
+		}
+	}
+
+	/* reject off1 + off2 >= 6 */
+	reject_offsets(insns, ARRAY_SIZE(insns), 8 * 3, 8 * 3);
+	reject_offsets(insns, ARRAY_SIZE(insns), 8 * 7, 8 * 0);
+	reject_offsets(insns, ARRAY_SIZE(insns), 8 * 0, 8 * 7);
+
+	/* reject (off1 + off2) % 8 != 0 */
+	reject_offsets(insns, ARRAY_SIZE(insns), 3, 3);
+	reject_offsets(insns, ARRAY_SIZE(insns), 7, 0);
+	reject_offsets(insns, ARRAY_SIZE(insns), 0, 7);
+}
+
 void test_bpf_gotox(void)
 {
 	struct bpf_gotox *skel;
@@ -288,5 +490,11 @@ void test_bpf_gotox(void)
 	if (test__start_subtest("one-map-two-jumps"))
 		__subtest(skel, check_one_map_two_jumps);
 
+	if (test__start_subtest("check-ldimm64-off"))
+		__subtest(skel, check_ldimm64_off_load);
+
+	if (test__start_subtest("check-ldimm64-off-gotox"))
+		__subtest(skel, check_ldimm64_off_gotox);
+
 	bpf_gotox__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
index dd6512fa652b..215878ea04de 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
@@ -19,6 +19,10 @@ struct {
 	{ "change_timeout_after_alloc", "kernel function bpf_ct_change_timeout args#0 expected pointer to STRUCT nf_conn but" },
 	{ "change_status_after_alloc", "kernel function bpf_ct_change_status args#0 expected pointer to STRUCT nf_conn but" },
 	{ "write_not_allowlisted_field", "no write support to nf_conn at off" },
+	{ "lookup_null_bpf_tuple", "Possibly NULL pointer passed to trusted arg1" },
+	{ "lookup_null_bpf_opts", "Possibly NULL pointer passed to trusted arg3" },
+	{ "xdp_lookup_null_bpf_tuple", "Possibly NULL pointer passed to trusted arg1" },
+	{ "xdp_lookup_null_bpf_opts", "Possibly NULL pointer passed to trusted arg3" },
 };
 
 enum {
@@ -111,7 +115,6 @@ static void test_bpf_nf_ct(int mode)
 	if (!ASSERT_OK(err, "bpf_prog_test_run"))
 		goto end;
 
-	ASSERT_EQ(skel->bss->test_einval_bpf_tuple, -EINVAL, "Test EINVAL for NULL bpf_tuple");
 	ASSERT_EQ(skel->bss->test_einval_reserved, -EINVAL, "Test EINVAL for reserved not set to 0");
 	ASSERT_EQ(skel->bss->test_einval_reserved_new, -EINVAL, "Test EINVAL for reserved in new struct not set to 0");
 	ASSERT_EQ(skel->bss->test_einval_netns_id, -EINVAL, "Test EINVAL for netns_id < -1");
diff --git a/tools/testing/selftests/bpf/prog_tests/bpftool_maps_access.c b/tools/testing/selftests/bpf/prog_tests/bpftool_maps_access.c
new file mode 100644
index 000000000000..e0eb869cb1b4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpftool_maps_access.c
@@ -0,0 +1,371 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <stdint.h>
+#include <sys/stat.h>
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <bpf/libbpf.h>
+#include <bpftool_helpers.h>
+#include <test_progs.h>
+#include <bpf/bpf.h>
+#include "security_bpf_map.skel.h"
+
+#define PROTECTED_MAP_NAME	"prot_map"
+#define UNPROTECTED_MAP_NAME	"not_prot_map"
+#define BPF_ITER_FILE		"bpf_iter_map_elem.bpf.o"
+#define BPFFS_PIN_DIR		"/sys/fs/bpf/test_bpftool_map"
+#define INNER_MAP_NAME		"inner_map_tt"
+#define OUTER_MAP_NAME		"outer_map_tt"
+
+#define MAP_NAME_MAX_LEN	64
+#define PATH_MAX_LEN		128
+
+enum map_protection {
+	PROTECTED,
+	UNPROTECTED
+};
+
+struct test_desc {
+	char *name;
+	enum map_protection protection;
+	struct bpf_map *map;
+	char *map_name;
+	bool pinned;
+	char pin_path[PATH_MAX_LEN];
+	bool write_must_fail;
+};
+
+static struct security_bpf_map *general_setup(void)
+{
+	struct security_bpf_map *skel;
+	uint32_t key, value;
+	int ret, i;
+
+	skel = security_bpf_map__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open and load skeleton"))
+		goto end;
+
+	struct bpf_map *maps[] = {skel->maps.prot_map, skel->maps.not_prot_map};
+
+	ret = security_bpf_map__attach(skel);
+	if (!ASSERT_OK(ret, "attach maps security programs"))
+		goto end_destroy;
+
+	for (i = 0; i < sizeof(maps)/sizeof(struct bpf_map *); i++) {
+		for (key = 0; key < 2; key++) {
+			int ret = bpf_map__update_elem(maps[i], &key,
+					sizeof(key), &key, sizeof(key),
+					0);
+			if (!ASSERT_OK(ret, "set initial map value"))
+				goto end_destroy;
+		}
+	}
+
+	key = 0;
+	value = 1;
+	ret = bpf_map__update_elem(skel->maps.prot_status_map, &key,
+			sizeof(key), &value, sizeof(value), 0);
+	if (!ASSERT_OK(ret, "configure map protection"))
+		goto end_destroy;
+
+	if (!ASSERT_OK(mkdir(BPFFS_PIN_DIR, S_IFDIR), "create bpffs pin dir"))
+		goto end_destroy;
+
+	return skel;
+end_destroy:
+	security_bpf_map__destroy(skel);
+end:
+	return NULL;
+}
+
+static void general_cleanup(struct security_bpf_map *skel)
+{
+	rmdir(BPFFS_PIN_DIR);
+	security_bpf_map__destroy(skel);
+}
+
+static void update_test_desc(struct security_bpf_map *skel,
+			      struct test_desc *test)
+{
+	/* Now that the skeleton is loaded, update all missing fields to
+	 * have the subtest properly configured
+	 */
+	if (test->protection == PROTECTED) {
+		test->map = skel->maps.prot_map;
+		test->map_name = PROTECTED_MAP_NAME;
+	} else {
+		test->map = skel->maps.not_prot_map;
+		test->map_name = UNPROTECTED_MAP_NAME;
+	}
+}
+
+static int test_setup(struct security_bpf_map *skel, struct test_desc *desc)
+{
+	int ret;
+
+	update_test_desc(skel, desc);
+
+	if (desc->pinned) {
+		ret = snprintf(desc->pin_path, PATH_MAX_LEN, "%s/%s", BPFFS_PIN_DIR,
+				desc->name);
+		if (!ASSERT_GT(ret, 0, "format pin path"))
+			return 1;
+		ret = bpf_map__pin(desc->map, desc->pin_path);
+		if (!ASSERT_OK(ret, "pin map"))
+			return 1;
+	}
+
+	return 0;
+}
+
+static void test_cleanup(struct test_desc *desc)
+{
+	if (desc->pinned)
+		bpf_map__unpin(desc->map, NULL);
+}
+
+static int lookup_map_value(char *map_handle)
+{
+	char cmd[MAX_BPFTOOL_CMD_LEN];
+	int ret = 0;
+
+	ret = snprintf(cmd, MAX_BPFTOOL_CMD_LEN, "map lookup %s key 0 0 0 0",
+			map_handle);
+	if (!ASSERT_GT(ret, 0, "format map lookup cmd"))
+		return 1;
+	return run_bpftool_command(cmd);
+}
+
+static int read_map_btf_data(char *map_handle)
+{
+	char cmd[MAX_BPFTOOL_CMD_LEN];
+	int ret = 0;
+
+	ret = snprintf(cmd, MAX_BPFTOOL_CMD_LEN, "btf dump map %s",
+			map_handle);
+	if (!ASSERT_GT(ret, 0, "format map btf dump cmd"))
+		return 1;
+	return run_bpftool_command(cmd);
+}
+
+static int write_map_value(char *map_handle)
+{
+	char cmd[MAX_BPFTOOL_CMD_LEN];
+	int ret = 0;
+
+	ret = snprintf(cmd, MAX_BPFTOOL_CMD_LEN,
+		       "map update %s key 0 0 0 0 value 1 1 1 1", map_handle);
+	if (!ASSERT_GT(ret, 0, "format value write cmd"))
+		return 1;
+	return run_bpftool_command(cmd);
+}
+
+static int delete_map_value(char *map_handle)
+{
+	char cmd[MAX_BPFTOOL_CMD_LEN];
+	int ret = 0;
+
+	ret = snprintf(cmd, MAX_BPFTOOL_CMD_LEN,
+		       "map delete %s key 0 0 0 0", map_handle);
+	if (!ASSERT_GT(ret, 0, "format value deletion cmd"))
+		return 1;
+	return run_bpftool_command(cmd);
+}
+
+static int iterate_on_map_values(char *map_handle, char *iter_pin_path)
+{
+	char cmd[MAX_BPFTOOL_CMD_LEN];
+	int ret = 0;
+
+
+	ret = snprintf(cmd, MAX_BPFTOOL_CMD_LEN, "iter pin %s %s map %s",
+		       BPF_ITER_FILE, iter_pin_path, map_handle);
+	if (!ASSERT_GT(ret, 0, "format iterator creation cmd"))
+		return 1;
+	ret = run_bpftool_command(cmd);
+	if (ret)
+		return ret;
+	ret = snprintf(cmd, MAP_NAME_MAX_LEN, "cat %s", iter_pin_path);
+	if (ret < 0)
+		goto cleanup;
+	ret = system(cmd);
+
+cleanup:
+	unlink(iter_pin_path);
+	return ret;
+}
+
+static int create_inner_map(void)
+{
+	char cmd[MAX_BPFTOOL_CMD_LEN];
+	int ret = 0;
+
+	ret = snprintf(
+		cmd, MAX_BPFTOOL_CMD_LEN,
+		"map create %s/%s type array key 4 value 4 entries 4 name %s",
+		BPFFS_PIN_DIR, INNER_MAP_NAME, INNER_MAP_NAME);
+	if (!ASSERT_GT(ret, 0, "format inner map create cmd"))
+		return 1;
+	return run_bpftool_command(cmd);
+}
+
+static int create_outer_map(void)
+{
+	char cmd[MAX_BPFTOOL_CMD_LEN];
+	int ret = 0;
+
+	ret = snprintf(
+		cmd, MAX_BPFTOOL_CMD_LEN,
+		"map create %s/%s type hash_of_maps key 4 value 4 entries 2 name %s inner_map name %s",
+		BPFFS_PIN_DIR, OUTER_MAP_NAME, OUTER_MAP_NAME, INNER_MAP_NAME);
+	if (!ASSERT_GT(ret, 0, "format outer map create cmd"))
+		return 1;
+	return run_bpftool_command(cmd);
+}
+
+static void delete_pinned_map(char *map_name)
+{
+	char pin_path[PATH_MAX_LEN];
+	int ret;
+
+	ret = snprintf(pin_path, PATH_MAX_LEN, "%s/%s", BPFFS_PIN_DIR,
+		       map_name);
+	if (ret >= 0)
+		unlink(pin_path);
+}
+
+static int add_outer_map_entry(int key)
+{
+	char cmd[MAX_BPFTOOL_CMD_LEN];
+	int ret = 0;
+
+	ret = snprintf(
+		cmd, MAX_BPFTOOL_CMD_LEN,
+		"map update pinned %s/%s key %d 0 0 0 value name %s",
+		BPFFS_PIN_DIR, OUTER_MAP_NAME, key, INNER_MAP_NAME);
+	if (!ASSERT_GT(ret, 0, "format outer map value addition cmd"))
+		return 1;
+	return run_bpftool_command(cmd);
+}
+
+static void test_basic_access(struct test_desc *desc)
+{
+	char map_handle[MAP_NAME_MAX_LEN];
+	char iter_pin_path[PATH_MAX_LEN];
+	int ret;
+
+	if (desc->pinned)
+		ret = snprintf(map_handle, MAP_NAME_MAX_LEN, "pinned %s",
+			       desc->pin_path);
+	else
+		ret = snprintf(map_handle, MAP_NAME_MAX_LEN, "name %s",
+			       desc->map_name);
+	if (!ASSERT_GT(ret, 0, "format map handle"))
+		return;
+
+	ret = lookup_map_value(map_handle);
+	ASSERT_OK(ret, "read map value");
+
+	ret = read_map_btf_data(map_handle);
+	ASSERT_OK(ret, "read map btf data");
+
+	ret = write_map_value(map_handle);
+	ASSERT_OK(desc->write_must_fail ? !ret : ret, "write map value");
+
+	ret = delete_map_value(map_handle);
+	ASSERT_OK(desc->write_must_fail ? !ret : ret, "delete map value");
+	/* Restore deleted value */
+	if (!ret)
+		write_map_value(map_handle);
+
+	ret = snprintf(iter_pin_path, PATH_MAX_LEN, "%s/iter", BPFFS_PIN_DIR);
+	if (ASSERT_GT(ret, 0, "format iter pin path")) {
+		ret = iterate_on_map_values(map_handle, iter_pin_path);
+		ASSERT_OK(ret, "iterate on map values");
+	}
+}
+
+static void test_create_nested_maps(void)
+{
+	if (!ASSERT_OK(create_inner_map(), "create inner map"))
+		return;
+	if (!ASSERT_OK(create_outer_map(), "create outer map"))
+		goto end_cleanup_inner;
+	ASSERT_OK(add_outer_map_entry(0), "add a first entry in outer map");
+	ASSERT_OK(add_outer_map_entry(1), "add a second entry in outer map");
+	ASSERT_NEQ(add_outer_map_entry(2), 0, "add a third entry in outer map");
+
+	delete_pinned_map(OUTER_MAP_NAME);
+end_cleanup_inner:
+	delete_pinned_map(INNER_MAP_NAME);
+}
+
+static void test_btf_list(void)
+{
+	ASSERT_OK(run_bpftool_command("btf list"), "list btf data");
+}
+
+static struct test_desc tests[] = {
+	{
+		.name = "unprotected_unpinned",
+		.protection = UNPROTECTED,
+		.map_name = UNPROTECTED_MAP_NAME,
+		.pinned = false,
+		.write_must_fail = false,
+	},
+	{
+		.name = "unprotected_pinned",
+		.protection = UNPROTECTED,
+		.map_name = UNPROTECTED_MAP_NAME,
+		.pinned = true,
+		.write_must_fail = false,
+	},
+	{
+		.name = "protected_unpinned",
+		.protection = PROTECTED,
+		.map_name = UNPROTECTED_MAP_NAME,
+		.pinned = false,
+		.write_must_fail = true,
+	},
+	{
+		.name = "protected_pinned",
+		.protection = PROTECTED,
+		.map_name = UNPROTECTED_MAP_NAME,
+		.pinned = true,
+		.write_must_fail = true,
+	}
+};
+
+static const size_t tests_count = ARRAY_SIZE(tests);
+
+void test_bpftool_maps_access(void)
+{
+	struct security_bpf_map *skel;
+	struct test_desc *current;
+	int i;
+
+	skel = general_setup();
+	if (!ASSERT_OK_PTR(skel, "prepare programs"))
+		goto cleanup;
+
+	for (i = 0; i < tests_count; i++) {
+		current = &tests[i];
+		if (!test__start_subtest(current->name))
+			continue;
+		if (ASSERT_OK(test_setup(skel, current), "subtest setup")) {
+			test_basic_access(current);
+			test_cleanup(current);
+		}
+	}
+	if (test__start_subtest("nested_maps"))
+		test_create_nested_maps();
+	if (test__start_subtest("btf_list"))
+		test_btf_list();
+
+cleanup:
+	general_cleanup(skel);
+}
+
diff --git a/tools/testing/selftests/bpf/prog_tests/bpftool_metadata.c b/tools/testing/selftests/bpf/prog_tests/bpftool_metadata.c
new file mode 100644
index 000000000000..408ace90dc7e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpftool_metadata.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <bpftool_helpers.h>
+#include <test_progs.h>
+#include <linux/bpf.h>
+#include <string.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/stat.h>
+#include <stdbool.h>
+
+#define BPFFS_DIR	"/sys/fs/bpf/test_metadata"
+#define BPFFS_USED	BPFFS_DIR "/used"
+#define BPFFS_UNUSED	BPFFS_DIR "/unused"
+
+#define BPF_FILE_USED		"metadata_used.bpf.o"
+#define BPF_FILE_UNUSED		"metadata_unused.bpf.o"
+#define METADATA_MAP_NAME	"metadata.rodata"
+
+#define MAX_BPFTOOL_OUTPUT_LEN	(64*1024)
+
+#define MAX_TOKENS_TO_CHECK	3
+static char output[MAX_BPFTOOL_OUTPUT_LEN];
+
+struct test_desc {
+	char *name;
+	char *bpf_prog;
+	char *bpffs_path;
+	char *expected_output[MAX_TOKENS_TO_CHECK];
+	char *expected_output_json[MAX_TOKENS_TO_CHECK];
+	char *metadata_map_name;
+};
+
+static int setup(struct test_desc *test)
+{
+	return mkdir(BPFFS_DIR, 0700);
+}
+
+static void cleanup(struct test_desc *test)
+{
+	unlink(test->bpffs_path);
+	rmdir(BPFFS_DIR);
+}
+
+static int check_metadata(char *buf, char * const *tokens, int count)
+{
+	int i;
+
+	for (i = 0; i < count && tokens[i]; i++)
+		if (!strstr(buf, tokens[i]))
+			return 1;
+
+	return 0;
+}
+
+static void run_test(struct test_desc *test)
+{
+	int ret;
+	char cmd[MAX_BPFTOOL_CMD_LEN];
+
+	ret = snprintf(cmd, MAX_BPFTOOL_CMD_LEN, "prog load %s %s",
+			test->bpf_prog, test->bpffs_path);
+	if (!ASSERT_GT(ret, 0, "format prog insert command"))
+		return;
+	ret = run_bpftool_command(cmd);
+	if (!ASSERT_OK(ret, "load program"))
+		return;
+
+	/* Check output with default format */
+	ret = snprintf(cmd, MAX_BPFTOOL_CMD_LEN, "prog show pinned %s",
+		       test->bpffs_path);
+	if (!ASSERT_GT(ret, 0, "format pinned prog check command"))
+		return;
+	ret = get_bpftool_command_output(cmd, output,
+			MAX_BPFTOOL_OUTPUT_LEN);
+	if (ASSERT_OK(ret, "get program info")) {
+		ret = check_metadata(output, test->expected_output,
+				ARRAY_SIZE(test->expected_output));
+		ASSERT_OK(ret, "find metadata");
+	}
+
+	/* Check output with json format */
+	ret = snprintf(cmd, MAX_BPFTOOL_CMD_LEN, "prog -j show pinned %s",
+		       test->bpffs_path);
+	if (!ASSERT_GT(ret, 0, "format pinned prog check command in json"))
+		return;
+	ret = get_bpftool_command_output(cmd, output,
+					 MAX_BPFTOOL_OUTPUT_LEN);
+	if (ASSERT_OK(ret, "get program info in json")) {
+		ret = check_metadata(output, test->expected_output_json,
+				ARRAY_SIZE(test->expected_output_json));
+		ASSERT_OK(ret, "find metadata in json");
+	}
+
+	/* Check that the corresponding map can be found and accessed */
+	ret = snprintf(cmd, MAX_BPFTOOL_CMD_LEN, "map show name %s",
+		       test->metadata_map_name);
+	if (!ASSERT_GT(ret, 0, "format map check command"))
+		return;
+	ASSERT_OK(run_bpftool_command(cmd), "access metadata map");
+}
+
+static struct test_desc tests[] = {
+	{
+		.name = "metadata_unused",
+		.bpf_prog = BPF_FILE_UNUSED,
+		.bpffs_path = BPFFS_UNUSED,
+		.expected_output = {
+			"a = \"foo\"",
+			"b = 1"
+		},
+		.expected_output_json = {
+			"\"metadata\":{\"a\":\"foo\",\"b\":1}"
+		},
+		.metadata_map_name = METADATA_MAP_NAME
+	},
+	{
+		.name = "metadata_used",
+		.bpf_prog = BPF_FILE_USED,
+		.bpffs_path = BPFFS_USED,
+		.expected_output = {
+			"a = \"bar\"",
+			"b = 2"
+		},
+		.expected_output_json = {
+			"\"metadata\":{\"a\":\"bar\",\"b\":2}"
+		},
+		.metadata_map_name = METADATA_MAP_NAME
+	}
+};
+static const int tests_count = ARRAY_SIZE(tests);
+
+void test_bpftool_metadata(void)
+{
+	int i;
+
+	for (i = 0; i < tests_count; i++) {
+		if (!test__start_subtest(tests[i].name))
+			continue;
+		if (ASSERT_OK(setup(&tests[i]), "setup bpffs pin dir")) {
+			run_test(&tests[i]);
+			cleanup(&tests[i]);
+		}
+	}
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index 10cba526d3e6..f1642794f70e 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -875,8 +875,8 @@ 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, "bpf_cgrp_storage_busy", int, BTF_F_COMPACT,
-			  "static int bpf_cgrp_storage_busy = (int)2", 2);
+	TEST_BTF_DUMP_VAR(btf, d, NULL, str, "bpf_bprintf_nest_level", int, BTF_F_COMPACT,
+			  "static int bpf_bprintf_nest_level = (int)2", 2);
 }
 
 struct btf_dump_string_ctx {
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_permute.c b/tools/testing/selftests/bpf/prog_tests/btf_permute.c
new file mode 100644
index 000000000000..04ade5ad77ac
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_permute.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Xiaomi */
+
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include "btf_helpers.h"
+
+static void permute_base_check(struct btf *btf)
+{
+	VALIDATE_RAW_BTF(
+		btf,
+		"[1] STRUCT 's2' size=4 vlen=1\n"
+		"\t'm' type_id=4 bits_offset=0",
+		"[2] FUNC 'f' type_id=6 linkage=static",
+		"[3] PTR '(anon)' type_id=4",
+		"[4] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[5] STRUCT 's1' size=4 vlen=1\n"
+		"\t'm' type_id=4 bits_offset=0",
+		"[6] FUNC_PROTO '(anon)' ret_type_id=4 vlen=1\n"
+		"\t'p' type_id=3");
+}
+
+/* Ensure btf__permute works as expected in the base-BTF scenario */
+static void test_permute_base(void)
+{
+	struct btf *btf;
+	__u32 permute_ids[7];
+	int err;
+
+	btf = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf, "empty_main_btf"))
+		return;
+
+	btf__add_int(btf, "int", 4, BTF_INT_SIGNED);	/* [1] int */
+	btf__add_ptr(btf, 1);				/* [2] ptr to int */
+	btf__add_struct(btf, "s1", 4);			/* [3] struct s1 { */
+	btf__add_field(btf, "m", 1, 0, 0);		/*       int m; */
+							/* } */
+	btf__add_struct(btf, "s2", 4);			/* [4] struct s2 { */
+	btf__add_field(btf, "m", 1, 0, 0);		/*       int m; */
+							/* } */
+	btf__add_func_proto(btf, 1);			/* [5] int (*)(int *p); */
+	btf__add_func_param(btf, "p", 2);
+	btf__add_func(btf, "f", BTF_FUNC_STATIC, 5);	/* [6] int f(int *p); */
+
+	VALIDATE_RAW_BTF(
+		btf,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] STRUCT 's1' size=4 vlen=1\n"
+		"\t'm' type_id=1 bits_offset=0",
+		"[4] STRUCT 's2' size=4 vlen=1\n"
+		"\t'm' type_id=1 bits_offset=0",
+		"[5] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p' type_id=2",
+		"[6] FUNC 'f' type_id=5 linkage=static");
+
+	permute_ids[0] = 0; /* [0] -> [0] */
+	permute_ids[1] = 4; /* [1] -> [4] */
+	permute_ids[2] = 3; /* [2] -> [3] */
+	permute_ids[3] = 5; /* [3] -> [5] */
+	permute_ids[4] = 1; /* [4] -> [1] */
+	permute_ids[5] = 6; /* [5] -> [6] */
+	permute_ids[6] = 2; /* [6] -> [2] */
+	err = btf__permute(btf, permute_ids, ARRAY_SIZE(permute_ids), NULL);
+	if (!ASSERT_OK(err, "btf__permute_base"))
+		goto done;
+	permute_base_check(btf);
+
+	/* ids[0] must be 0 for base BTF */
+	permute_ids[0] = 4; /* [0] -> [0] */
+	permute_ids[1] = 0; /* [1] -> [4] */
+	permute_ids[2] = 3; /* [2] -> [3] */
+	permute_ids[3] = 5; /* [3] -> [5] */
+	permute_ids[4] = 1; /* [4] -> [1] */
+	permute_ids[5] = 6; /* [5] -> [6] */
+	permute_ids[6] = 2; /* [6] -> [2] */
+	err = btf__permute(btf, permute_ids, ARRAY_SIZE(permute_ids), NULL);
+	if (!ASSERT_ERR(err, "btf__permute_base"))
+		goto done;
+	/* BTF is not modified */
+	permute_base_check(btf);
+
+	/* id_map_cnt is invalid */
+	permute_ids[0] = 0; /* [0] -> [0] */
+	permute_ids[1] = 4; /* [1] -> [4] */
+	permute_ids[2] = 3; /* [2] -> [3] */
+	permute_ids[3] = 5; /* [3] -> [5] */
+	permute_ids[4] = 1; /* [4] -> [1] */
+	permute_ids[5] = 6; /* [5] -> [6] */
+	permute_ids[6] = 2; /* [6] -> [2] */
+	err = btf__permute(btf, permute_ids, ARRAY_SIZE(permute_ids) - 1, NULL);
+	if (!ASSERT_ERR(err, "btf__permute_base"))
+		goto done;
+	/* BTF is not modified */
+	permute_base_check(btf);
+
+	/* Multiple types can not be mapped to the same ID */
+	permute_ids[0] = 0;
+	permute_ids[1] = 4;
+	permute_ids[2] = 4;
+	permute_ids[3] = 5;
+	permute_ids[4] = 1;
+	permute_ids[5] = 6;
+	permute_ids[6] = 2;
+	err = btf__permute(btf, permute_ids, ARRAY_SIZE(permute_ids), NULL);
+	if (!ASSERT_ERR(err, "btf__permute_base"))
+		goto done;
+	/* BTF is not modified */
+	permute_base_check(btf);
+
+	/* Type ID must be valid */
+	permute_ids[0] = 0;
+	permute_ids[1] = 4;
+	permute_ids[2] = 3;
+	permute_ids[3] = 5;
+	permute_ids[4] = 1;
+	permute_ids[5] = 7;
+	permute_ids[6] = 2;
+	err = btf__permute(btf, permute_ids, ARRAY_SIZE(permute_ids), NULL);
+	if (!ASSERT_ERR(err, "btf__permute_base"))
+		goto done;
+	/* BTF is not modified */
+	permute_base_check(btf);
+
+done:
+	btf__free(btf);
+}
+
+static void permute_split_check(struct btf *btf)
+{
+	VALIDATE_RAW_BTF(
+		btf,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] STRUCT 's2' size=4 vlen=1\n"
+		"\t'm' type_id=1 bits_offset=0",
+		"[4] FUNC 'f' type_id=5 linkage=static",
+		"[5] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p' type_id=2",
+		"[6] STRUCT 's1' size=4 vlen=1\n"
+		"\t'm' type_id=1 bits_offset=0");
+}
+
+/* Ensure btf__permute works as expected in the split-BTF scenario */
+static void test_permute_split(void)
+{
+	struct btf *split_btf = NULL, *base_btf = NULL;
+	__u32 permute_ids[4];
+	int err, start_id;
+
+	base_btf = btf__new_empty();
+	if (!ASSERT_OK_PTR(base_btf, "empty_main_btf"))
+		return;
+
+	btf__add_int(base_btf, "int", 4, BTF_INT_SIGNED);	/* [1] int */
+	btf__add_ptr(base_btf, 1);				/* [2] ptr to int */
+	VALIDATE_RAW_BTF(
+		base_btf,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1");
+	split_btf = btf__new_empty_split(base_btf);
+	if (!ASSERT_OK_PTR(split_btf, "empty_split_btf"))
+		goto cleanup;
+	btf__add_struct(split_btf, "s1", 4);			/* [3] struct s1 { */
+	btf__add_field(split_btf, "m", 1, 0, 0);		/*   int m; */
+								/* } */
+	btf__add_struct(split_btf, "s2", 4);			/* [4] struct s2 { */
+	btf__add_field(split_btf, "m", 1, 0, 0);		/*   int m; */
+								/* } */
+	btf__add_func_proto(split_btf, 1);			/* [5] int (*)(int p); */
+	btf__add_func_param(split_btf, "p", 2);
+	btf__add_func(split_btf, "f", BTF_FUNC_STATIC, 5);	/* [6] int f(int *p); */
+
+	VALIDATE_RAW_BTF(
+		split_btf,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] STRUCT 's1' size=4 vlen=1\n"
+		"\t'm' type_id=1 bits_offset=0",
+		"[4] STRUCT 's2' size=4 vlen=1\n"
+		"\t'm' type_id=1 bits_offset=0",
+		"[5] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p' type_id=2",
+		"[6] FUNC 'f' type_id=5 linkage=static");
+
+	start_id = btf__type_cnt(base_btf);
+	permute_ids[3 - start_id] = 6; /* [3] -> [6] */
+	permute_ids[4 - start_id] = 3; /* [4] -> [3] */
+	permute_ids[5 - start_id] = 5; /* [5] -> [5] */
+	permute_ids[6 - start_id] = 4; /* [6] -> [4] */
+	err = btf__permute(split_btf, permute_ids, ARRAY_SIZE(permute_ids), NULL);
+	if (!ASSERT_OK(err, "btf__permute_split"))
+		goto cleanup;
+	permute_split_check(split_btf);
+
+	/*
+	 * For split BTF, id_map_cnt must equal to the number of types
+	 * added on top of base BTF
+	 */
+	permute_ids[3 - start_id] = 4;
+	permute_ids[4 - start_id] = 3;
+	permute_ids[5 - start_id] = 5;
+	permute_ids[6 - start_id] = 6;
+	err = btf__permute(split_btf, permute_ids, ARRAY_SIZE(permute_ids) - 1, NULL);
+	if (!ASSERT_ERR(err, "btf__permute_split"))
+		goto cleanup;
+	/* BTF is not modified */
+	permute_split_check(split_btf);
+
+	/* Multiple types can not be mapped to the same ID */
+	permute_ids[3 - start_id] = 4;
+	permute_ids[4 - start_id] = 3;
+	permute_ids[5 - start_id] = 3;
+	permute_ids[6 - start_id] = 6;
+	err = btf__permute(split_btf, permute_ids, ARRAY_SIZE(permute_ids), NULL);
+	if (!ASSERT_ERR(err, "btf__permute_split"))
+		goto cleanup;
+	/* BTF is not modified */
+	permute_split_check(split_btf);
+
+	/* Can not map to base ID */
+	permute_ids[3 - start_id] = 4;
+	permute_ids[4 - start_id] = 2;
+	permute_ids[5 - start_id] = 5;
+	permute_ids[6 - start_id] = 6;
+	err = btf__permute(split_btf, permute_ids, ARRAY_SIZE(permute_ids), NULL);
+	if (!ASSERT_ERR(err, "btf__permute_split"))
+		goto cleanup;
+	/* BTF is not modified */
+	permute_split_check(split_btf);
+
+cleanup:
+	btf__free(split_btf);
+	btf__free(base_btf);
+}
+
+void test_btf_permute(void)
+{
+	if (test__start_subtest("permute_base"))
+		test_permute_base();
+	if (test__start_subtest("permute_split"))
+		test_permute_split();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c b/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c
index 574d9a0cdc8e..0f88a9d00a22 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c
@@ -190,6 +190,16 @@ static void test_walk_self_only(struct cgroup_iter *skel)
 			      BPF_CGROUP_ITER_SELF_ONLY, "self_only");
 }
 
+static void test_walk_children(struct cgroup_iter *skel)
+{
+	snprintf(expected_output, sizeof(expected_output),
+		 PROLOGUE "%8llu\n%8llu\n" EPILOGUE, cg_id[CHILD1],
+		 cg_id[CHILD2]);
+
+	read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[PARENT],
+			      BPF_CGROUP_ITER_CHILDREN, "children");
+}
+
 static void test_walk_dead_self_only(struct cgroup_iter *skel)
 {
 	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
@@ -325,6 +335,8 @@ void test_cgroup_iter(void)
 		test_walk_dead_self_only(skel);
 	if (test__start_subtest("cgroup_iter__self_only_css_task"))
 		test_walk_self_only_css_task();
+	if (test__start_subtest("cgroup_iter__children"))
+		test_walk_children(skel);
 
 out:
 	cgroup_iter__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_iter_memcg.c b/tools/testing/selftests/bpf/prog_tests/cgroup_iter_memcg.c
new file mode 100644
index 000000000000..a5afd16705f0
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_iter_memcg.c
@@ -0,0 +1,223 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <bpf/libbpf.h>
+#include <bpf/btf.h>
+#include <fcntl.h>
+#include <sys/mman.h>
+#include <unistd.h>
+#include "cgroup_helpers.h"
+#include "cgroup_iter_memcg.h"
+#include "cgroup_iter_memcg.skel.h"
+
+static int read_stats(struct bpf_link *link)
+{
+	int fd, ret = 0;
+	ssize_t bytes;
+
+	fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_OK_FD(fd, "bpf_iter_create"))
+		return 1;
+
+	/*
+	 * Invoke iter program by reading from its fd. We're not expecting any
+	 * data to be written by the bpf program so the result should be zero.
+	 * Results will be read directly through the custom data section
+	 * accessible through skel->data_query.memcg_query.
+	 */
+	bytes = read(fd, NULL, 0);
+	if (!ASSERT_EQ(bytes, 0, "read fd"))
+		ret = 1;
+
+	close(fd);
+	return ret;
+}
+
+static void test_anon(struct bpf_link *link, struct memcg_query *memcg_query)
+{
+	void *map;
+	size_t len;
+
+	len = sysconf(_SC_PAGESIZE) * 1024;
+
+	/*
+	 * Increase memcg anon usage by mapping and writing
+	 * to a new anon region.
+	 */
+	map = mmap(NULL, len, PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	if (!ASSERT_NEQ(map, MAP_FAILED, "mmap anon"))
+		return;
+
+	memset(map, 1, len);
+
+	if (!ASSERT_OK(read_stats(link), "read stats"))
+		goto cleanup;
+
+	ASSERT_GT(memcg_query->nr_anon_mapped, 0, "final anon mapped val");
+
+cleanup:
+	munmap(map, len);
+}
+
+static void test_file(struct bpf_link *link, struct memcg_query *memcg_query)
+{
+	void *map;
+	size_t len;
+	char *path;
+	int fd;
+
+	len = sysconf(_SC_PAGESIZE) * 1024;
+	path = "/tmp/test_cgroup_iter_memcg";
+
+	/*
+	 * Increase memcg file usage by creating and writing
+	 * to a mapped file.
+	 */
+	fd = open(path, O_CREAT | O_RDWR, 0644);
+	if (!ASSERT_OK_FD(fd, "open fd"))
+		return;
+	if (!ASSERT_OK(ftruncate(fd, len), "ftruncate"))
+		goto cleanup_fd;
+
+	map = mmap(NULL, len, PROT_WRITE, MAP_SHARED, fd, 0);
+	if (!ASSERT_NEQ(map, MAP_FAILED, "mmap file"))
+		goto cleanup_fd;
+
+	memset(map, 1, len);
+
+	if (!ASSERT_OK(read_stats(link), "read stats"))
+		goto cleanup_map;
+
+	ASSERT_GT(memcg_query->nr_file_pages, 0, "final file value");
+	ASSERT_GT(memcg_query->nr_file_mapped, 0, "final file mapped value");
+
+cleanup_map:
+	munmap(map, len);
+cleanup_fd:
+	close(fd);
+	unlink(path);
+}
+
+static void test_shmem(struct bpf_link *link, struct memcg_query *memcg_query)
+{
+	size_t len;
+	int fd;
+
+	len = sysconf(_SC_PAGESIZE) * 1024;
+
+	/*
+	 * Increase memcg shmem usage by creating and writing
+	 * to a shmem object.
+	 */
+	fd = shm_open("/tmp_shmem", O_CREAT | O_RDWR, 0644);
+	if (!ASSERT_OK_FD(fd, "shm_open"))
+		return;
+
+	if (!ASSERT_OK(fallocate(fd, 0, 0, len), "fallocate"))
+		goto cleanup;
+
+	if (!ASSERT_OK(read_stats(link), "read stats"))
+		goto cleanup;
+
+	ASSERT_GT(memcg_query->nr_shmem, 0, "final shmem value");
+
+cleanup:
+	close(fd);
+	shm_unlink("/tmp_shmem");
+}
+
+#define NR_PIPES 64
+static void test_kmem(struct bpf_link *link, struct memcg_query *memcg_query)
+{
+	int fds[NR_PIPES][2], i;
+
+	/*
+	 * Increase kmem value by creating pipes which will allocate some
+	 * kernel buffers.
+	 */
+	for (i = 0; i < NR_PIPES; i++) {
+		if (!ASSERT_OK(pipe(fds[i]), "pipe"))
+			goto cleanup;
+	}
+
+	if (!ASSERT_OK(read_stats(link), "read stats"))
+		goto cleanup;
+
+	ASSERT_GT(memcg_query->memcg_kmem, 0, "kmem value");
+
+cleanup:
+	for (i = i - 1; i >= 0; i--) {
+		close(fds[i][0]);
+		close(fds[i][1]);
+	}
+}
+
+static void test_pgfault(struct bpf_link *link, struct memcg_query *memcg_query)
+{
+	void *map;
+	size_t len;
+
+	len = sysconf(_SC_PAGESIZE) * 1024;
+
+	/* Create region to use for triggering a page fault. */
+	map = mmap(NULL, len, PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	if (!ASSERT_NEQ(map, MAP_FAILED, "mmap anon"))
+		return;
+
+	/* Trigger page fault. */
+	memset(map, 1, len);
+
+	if (!ASSERT_OK(read_stats(link), "read stats"))
+		goto cleanup;
+
+	ASSERT_GT(memcg_query->pgfault, 0, "final pgfault val");
+
+cleanup:
+	munmap(map, len);
+}
+
+void test_cgroup_iter_memcg(void)
+{
+	char *cgroup_rel_path = "/cgroup_iter_memcg_test";
+	struct cgroup_iter_memcg *skel;
+	struct bpf_link *link;
+	int cgroup_fd;
+
+	cgroup_fd = cgroup_setup_and_join(cgroup_rel_path);
+	if (!ASSERT_OK_FD(cgroup_fd, "cgroup_setup_and_join"))
+		return;
+
+	skel = cgroup_iter_memcg__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "cgroup_iter_memcg__open_and_load"))
+		goto cleanup_cgroup_fd;
+
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	union bpf_iter_link_info linfo = {
+		.cgroup.cgroup_fd = cgroup_fd,
+		.cgroup.order = BPF_CGROUP_ITER_SELF_ONLY,
+	};
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
+
+	link = bpf_program__attach_iter(skel->progs.cgroup_memcg_query, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter"))
+		goto cleanup_skel;
+
+	if (test__start_subtest("cgroup_iter_memcg__anon"))
+		test_anon(link, &skel->data_query->memcg_query);
+	if (test__start_subtest("cgroup_iter_memcg__shmem"))
+		test_shmem(link, &skel->data_query->memcg_query);
+	if (test__start_subtest("cgroup_iter_memcg__file"))
+		test_file(link, &skel->data_query->memcg_query);
+	if (test__start_subtest("cgroup_iter_memcg__kmem"))
+		test_kmem(link, &skel->data_query->memcg_query);
+	if (test__start_subtest("cgroup_iter_memcg__pgfault"))
+		test_pgfault(link, &skel->data_query->memcg_query);
+
+	bpf_link__destroy(link);
+cleanup_skel:
+	cgroup_iter_memcg__destroy(skel);
+cleanup_cgroup_fd:
+	close(cgroup_fd);
+	cleanup_cgroup_environment();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/dmabuf_iter.c b/tools/testing/selftests/bpf/prog_tests/dmabuf_iter.c
index e442be9dde7e..fb2cea710db3 100644
--- a/tools/testing/selftests/bpf/prog_tests/dmabuf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/dmabuf_iter.c
@@ -233,7 +233,7 @@ static void subtest_dmabuf_iter_check_lots_of_buffers(struct dmabuf_iter *skel)
 	while ((bytes_read = read(iter_fd, buf, sizeof(buf))) > 0)
 		total_bytes_read += bytes_read;
 
-	ASSERT_GT(total_bytes_read, getpagesize(), "total_bytes_read");
+	ASSERT_GT(total_bytes_read, 4096, "total_bytes_read");
 
 	close(iter_fd);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/exe_ctx.c b/tools/testing/selftests/bpf/prog_tests/exe_ctx.c
new file mode 100644
index 000000000000..aed6a6ef0876
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/exe_ctx.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2026 Valve Corporation.
+ * Author: Changwoo Min <changwoo@igalia.com>
+ */
+
+#include <test_progs.h>
+#include <sys/syscall.h>
+#include "test_ctx.skel.h"
+
+void test_exe_ctx(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	cpu_set_t old_cpuset, target_cpuset;
+	struct test_ctx *skel;
+	int err, prog_fd;
+
+	/* 1. Pin the current process to CPU 0. */
+	if (sched_getaffinity(0, sizeof(old_cpuset), &old_cpuset) == 0) {
+		CPU_ZERO(&target_cpuset);
+		CPU_SET(0, &target_cpuset);
+		ASSERT_OK(sched_setaffinity(0, sizeof(target_cpuset),
+					    &target_cpuset), "setaffinity");
+	}
+
+	skel = test_ctx__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto restore_affinity;
+
+	err = test_ctx__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	/* 2. When we run this, the kernel will execute the BPF prog on CPU 0. */
+	prog_fd = bpf_program__fd(skel->progs.trigger_all_contexts);
+	err = bpf_prog_test_run_opts(prog_fd, &opts);
+	ASSERT_OK(err, "test_run_trigger");
+
+	/* 3. Wait for the local CPU's softirq/tasklet to finish. */
+	for (int i = 0; i < 1000; i++) {
+		if (skel->bss->count_task > 0 &&
+		    skel->bss->count_hardirq > 0 &&
+		    skel->bss->count_softirq > 0)
+			break;
+		usleep(1000); /* Wait 1ms per iteration, up to 1 sec total */
+	}
+
+	/* On CPU 0, these should now all be non-zero. */
+	ASSERT_GT(skel->bss->count_task, 0, "task_ok");
+	ASSERT_GT(skel->bss->count_hardirq, 0, "hardirq_ok");
+	ASSERT_GT(skel->bss->count_softirq, 0, "softirq_ok");
+
+cleanup:
+	test_ctx__destroy(skel);
+
+restore_affinity:
+	ASSERT_OK(sched_setaffinity(0, sizeof(old_cpuset), &old_cpuset),
+		  "restore_affinity");
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fsession_test.c b/tools/testing/selftests/bpf/prog_tests/fsession_test.c
new file mode 100644
index 000000000000..a299aeb8cc2e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fsession_test.c
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 ChinaTelecom */
+#include <test_progs.h>
+#include "fsession_test.skel.h"
+
+static int check_result(struct fsession_test *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	int err, prog_fd;
+
+	/* Trigger test function calls */
+	prog_fd = bpf_program__fd(skel->progs.test1);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		return err;
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		return topts.retval;
+
+	for (int i = 0; i < sizeof(*skel->bss) / sizeof(__u64); i++) {
+		if (!ASSERT_EQ(((__u64 *)skel->bss)[i], 1, "test_result"))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void test_fsession_basic(void)
+{
+	struct fsession_test *skel = NULL;
+	int err;
+
+	skel = fsession_test__open();
+	if (!ASSERT_OK_PTR(skel, "fsession_test__open"))
+		return;
+
+	err = fsession_test__load(skel);
+	if (err == -EOPNOTSUPP) {
+		test__skip();
+		goto cleanup;
+	}
+	if (!ASSERT_OK(err, "fsession_test__load"))
+		goto cleanup;
+
+	err = fsession_test__attach(skel);
+	if (!ASSERT_OK(err, "fsession_attach"))
+		goto cleanup;
+
+	check_result(skel);
+cleanup:
+	fsession_test__destroy(skel);
+}
+
+static void test_fsession_reattach(void)
+{
+	struct fsession_test *skel = NULL;
+	int err;
+
+	skel = fsession_test__open();
+	if (!ASSERT_OK_PTR(skel, "fsession_test__open"))
+		return;
+
+	err = fsession_test__load(skel);
+	if (err == -EOPNOTSUPP) {
+		test__skip();
+		goto cleanup;
+	}
+	if (!ASSERT_OK(err, "fsession_test__load"))
+		goto cleanup;
+
+	/* first attach */
+	err = fsession_test__attach(skel);
+	if (!ASSERT_OK(err, "fsession_first_attach"))
+		goto cleanup;
+
+	if (check_result(skel))
+		goto cleanup;
+
+	/* detach */
+	fsession_test__detach(skel);
+
+	/* reset counters */
+	memset(skel->bss, 0, sizeof(*skel->bss));
+
+	/* second attach */
+	err = fsession_test__attach(skel);
+	if (!ASSERT_OK(err, "fsession_second_attach"))
+		goto cleanup;
+
+	if (check_result(skel))
+		goto cleanup;
+
+cleanup:
+	fsession_test__destroy(skel);
+}
+
+static void test_fsession_cookie(void)
+{
+	struct fsession_test *skel = NULL;
+	int err;
+
+	skel = fsession_test__open();
+	if (!ASSERT_OK_PTR(skel, "fsession_test__open"))
+		goto cleanup;
+
+	/*
+	 * The test_fsession_basic() will test the session cookie with
+	 * bpf_get_func_ip() case, so we need only check
+	 * the cookie without bpf_get_func_ip() case here
+	 */
+	bpf_program__set_autoload(skel->progs.test6, false);
+
+	err = fsession_test__load(skel);
+	if (err == -EOPNOTSUPP) {
+		test__skip();
+		goto cleanup;
+	}
+	if (!ASSERT_OK(err, "fsession_test__load"))
+		goto cleanup;
+
+	err = fsession_test__attach(skel);
+	if (!ASSERT_OK(err, "fsession_attach"))
+		goto cleanup;
+
+	skel->bss->test6_entry_result = 1;
+	skel->bss->test6_exit_result = 1;
+
+	check_result(skel);
+cleanup:
+	fsession_test__destroy(skel);
+}
+
+void test_fsession_test(void)
+{
+	if (test__start_subtest("fsession_test"))
+		test_fsession_basic();
+	if (test__start_subtest("fsession_reattach"))
+		test_fsession_reattach();
+	if (test__start_subtest("fsession_cookie"))
+		test_fsession_cookie();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c
index 64a9c95d4acf..96b27de05524 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c
@@ -33,11 +33,15 @@ void test_get_func_args_test(void)
 
 	ASSERT_EQ(topts.retval >> 16, 1, "test_run");
 	ASSERT_EQ(topts.retval & 0xffff, 1234 + 29, "test_run");
+	ASSERT_OK(trigger_module_test_read(1), "trigger_read");
 
 	ASSERT_EQ(skel->bss->test1_result, 1, "test1_result");
 	ASSERT_EQ(skel->bss->test2_result, 1, "test2_result");
 	ASSERT_EQ(skel->bss->test3_result, 1, "test3_result");
 	ASSERT_EQ(skel->bss->test4_result, 1, "test4_result");
+	ASSERT_EQ(skel->bss->test5_result, 1, "test5_result");
+	ASSERT_EQ(skel->bss->test6_result, 1, "test6_result");
+	ASSERT_EQ(skel->bss->test7_result, 1, "test7_result");
 
 cleanup:
 	get_func_args_test__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c
index c40242dfa8fb..7772a0f288d3 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c
@@ -46,6 +46,8 @@ static void test_function_entry(void)
 	ASSERT_EQ(skel->bss->test5_result, 1, "test5_result");
 	ASSERT_EQ(skel->bss->test7_result, 1, "test7_result");
 	ASSERT_EQ(skel->bss->test8_result, 1, "test8_result");
+	ASSERT_EQ(skel->bss->test9_entry_result, 1, "test9_entry_result");
+	ASSERT_EQ(skel->bss->test9_exit_result, 1, "test9_exit_result");
 
 cleanup:
 	get_func_ip_test__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c
index 3cea71f9c500..a539980a2fbe 100644
--- a/tools/testing/selftests/bpf/prog_tests/iters.c
+++ b/tools/testing/selftests/bpf/prog_tests/iters.c
@@ -253,6 +253,11 @@ static void subtest_css_iters(void)
 		{ "/cg1/cg2" },
 		{ "/cg1/cg2/cg3" },
 		{ "/cg1/cg2/cg3/cg4" },
+		{ "/cg1/cg5" },
+		{ "/cg1/cg5/cg6" },
+		{ "/cg1/cg7" },
+		{ "/cg1/cg7/cg8" },
+		{ "/cg1/cg7/cg8/cg9" },
 	};
 	int err, cg_nr = ARRAY_SIZE(cgs);
 	int i;
@@ -284,7 +289,8 @@ static void subtest_css_iters(void)
 
 	ASSERT_EQ(skel->bss->post_order_cnt, cg_nr, "post_order_cnt");
 	ASSERT_EQ(skel->bss->last_cg_id, get_cgroup_id(cgs[0].path), "last_cg_id");
-	ASSERT_EQ(skel->bss->tree_high, cg_nr - 1, "tree_high");
+	ASSERT_EQ(skel->bss->children_cnt, 3, "children_cnt");
+	ASSERT_EQ(skel->bss->tree_high, 3, "tree_high");
 	iters_css__detach(skel);
 cleanup:
 	cleanup_cgroup_environment();
diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_implicit_args.c b/tools/testing/selftests/bpf/prog_tests/kfunc_implicit_args.c
new file mode 100644
index 000000000000..5e4793c9c29a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_implicit_args.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include "kfunc_implicit_args.skel.h"
+
+void test_kfunc_implicit_args(void)
+{
+	RUN_TESTS(kfunc_implicit_args);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index 6cfaa978bc9a..9caef222e528 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -1,4 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include <sys/prctl.h>
 #include <test_progs.h>
 #include "kprobe_multi.skel.h"
 #include "trace_helpers.h"
@@ -540,6 +542,46 @@ cleanup:
 	kprobe_multi_override__destroy(skel);
 }
 
+static void test_override(void)
+{
+	struct kprobe_multi_override *skel = NULL;
+	int err;
+
+	skel = kprobe_multi_override__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "kprobe_multi_empty__open_and_load"))
+		goto cleanup;
+
+	skel->bss->pid = getpid();
+
+	/* no override */
+	err = prctl(0xffff, 0);
+	ASSERT_EQ(err, -1, "err");
+
+	/* kprobe.multi override */
+	skel->links.test_override = bpf_program__attach_kprobe_multi_opts(skel->progs.test_override,
+						SYS_PREFIX "sys_prctl", NULL);
+	if (!ASSERT_OK_PTR(skel->links.test_override, "bpf_program__attach_kprobe_multi_opts"))
+		goto cleanup;
+
+	err = prctl(0xffff, 0);
+	ASSERT_EQ(err, 123, "err");
+
+	bpf_link__destroy(skel->links.test_override);
+	skel->links.test_override = NULL;
+
+	/* kprobe override */
+	skel->links.test_kprobe_override = bpf_program__attach_kprobe(skel->progs.test_kprobe_override,
+							false, SYS_PREFIX "sys_prctl");
+	if (!ASSERT_OK_PTR(skel->links.test_kprobe_override, "bpf_program__attach_kprobe"))
+		goto cleanup;
+
+	err = prctl(0xffff, 0);
+	ASSERT_EQ(err, 123, "err");
+
+cleanup:
+	kprobe_multi_override__destroy(skel);
+}
+
 #ifdef __x86_64__
 static void test_attach_write_ctx(void)
 {
@@ -597,6 +639,8 @@ void test_kprobe_multi_test(void)
 		test_attach_api_fails();
 	if (test__start_subtest("attach_override"))
 		test_attach_override();
+	if (test__start_subtest("override"))
+		test_override();
 	if (test__start_subtest("session"))
 		test_session_skel_api();
 	if (test__start_subtest("session_cookie"))
diff --git a/tools/testing/selftests/bpf/prog_tests/map_kptr.c b/tools/testing/selftests/bpf/prog_tests/map_kptr.c
index 8743df599567..f372162c0280 100644
--- a/tools/testing/selftests/bpf/prog_tests/map_kptr.c
+++ b/tools/testing/selftests/bpf/prog_tests/map_kptr.c
@@ -131,6 +131,25 @@ static int kern_sync_rcu_tasks_trace(struct rcu_tasks_trace_gp *rcu)
 	return 0;
 }
 
+static void wait_for_map_release(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, lopts);
+	struct map_kptr *skel;
+	int ret;
+
+	skel = map_kptr__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "map_kptr__open_and_load"))
+		return;
+
+	do {
+		ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.count_ref), &lopts);
+		ASSERT_OK(ret, "count_ref ret");
+		ASSERT_OK(lopts.retval, "count_ref retval");
+	} while (skel->bss->num_of_refs != 2);
+
+	map_kptr__destroy(skel);
+}
+
 void serial_test_map_kptr(void)
 {
 	struct rcu_tasks_trace_gp *skel;
@@ -148,11 +167,15 @@ void serial_test_map_kptr(void)
 
 		ASSERT_OK(kern_sync_rcu_tasks_trace(skel), "sync rcu_tasks_trace");
 		ASSERT_OK(kern_sync_rcu(), "sync rcu");
+		wait_for_map_release();
+
 		/* Observe refcount dropping to 1 on bpf_map_free_deferred */
 		test_map_kptr_success(false);
 
 		ASSERT_OK(kern_sync_rcu_tasks_trace(skel), "sync rcu_tasks_trace");
 		ASSERT_OK(kern_sync_rcu(), "sync rcu");
+		wait_for_map_release();
+
 		/* Observe refcount dropping to 1 on synchronous delete elem */
 		test_map_kptr_success(true);
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
index 343da65864d6..a72ae0b29f6e 100644
--- a/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include "cgroup_helpers.h"
 #include "percpu_alloc_array.skel.h"
 #include "percpu_alloc_cgrp_local_storage.skel.h"
 #include "percpu_alloc_fail.skel.h"
@@ -115,6 +116,328 @@ static void test_failure(void) {
 	RUN_TESTS(percpu_alloc_fail);
 }
 
+static void test_percpu_map_op_cpu_flag(struct bpf_map *map, void *keys, size_t key_sz, u32 entries,
+					int nr_cpus, bool test_batch)
+{
+	size_t value_sz = sizeof(u32), value_sz_cpus, value_sz_total;
+	u32 *values = NULL, *values_percpu = NULL;
+	const u32 value = 0xDEADC0DE;
+	int i, j, cpu, map_fd, err;
+	u64 batch = 0, flags;
+	void *values_row;
+	u32 count, v;
+	LIBBPF_OPTS(bpf_map_batch_opts, batch_opts);
+
+	value_sz_cpus = value_sz * nr_cpus;
+	values = calloc(entries, value_sz_cpus);
+	if (!ASSERT_OK_PTR(values, "calloc values"))
+		return;
+
+	values_percpu = calloc(entries, roundup(value_sz, 8) * nr_cpus);
+	if (!ASSERT_OK_PTR(values_percpu, "calloc values_percpu")) {
+		free(values);
+		return;
+	}
+
+	value_sz_total = value_sz_cpus * entries;
+	memset(values, 0, value_sz_total);
+
+	map_fd = bpf_map__fd(map);
+	flags = BPF_F_CPU | BPF_F_ALL_CPUS;
+	err = bpf_map_lookup_elem_flags(map_fd, keys, values, flags);
+	if (!ASSERT_ERR(err, "bpf_map_lookup_elem_flags cpu|all_cpus"))
+		goto out;
+
+	err = bpf_map_update_elem(map_fd, keys, values, flags);
+	if (!ASSERT_ERR(err, "bpf_map_update_elem cpu|all_cpus"))
+		goto out;
+
+	flags = BPF_F_ALL_CPUS;
+	err = bpf_map_lookup_elem_flags(map_fd, keys, values, flags);
+	if (!ASSERT_ERR(err, "bpf_map_lookup_elem_flags all_cpus"))
+		goto out;
+
+	flags = BPF_F_LOCK | BPF_F_CPU;
+	err = bpf_map_lookup_elem_flags(map_fd, keys, values, flags);
+	if (!ASSERT_ERR(err, "bpf_map_lookup_elem_flags BPF_F_LOCK"))
+		goto out;
+
+	flags = BPF_F_LOCK | BPF_F_ALL_CPUS;
+	err = bpf_map_update_elem(map_fd, keys, values, flags);
+	if (!ASSERT_ERR(err, "bpf_map_update_elem BPF_F_LOCK"))
+		goto out;
+
+	flags = (u64)nr_cpus << 32 | BPF_F_CPU;
+	err = bpf_map_update_elem(map_fd, keys, values, flags);
+	if (!ASSERT_EQ(err, -ERANGE, "bpf_map_update_elem -ERANGE"))
+		goto out;
+
+	err = bpf_map__update_elem(map, keys, key_sz, values, value_sz, flags);
+	if (!ASSERT_EQ(err, -ERANGE, "bpf_map__update_elem -ERANGE"))
+		goto out;
+
+	err = bpf_map_lookup_elem_flags(map_fd, keys, values, flags);
+	if (!ASSERT_EQ(err, -ERANGE, "bpf_map_lookup_elem_flags -ERANGE"))
+		goto out;
+
+	err = bpf_map__lookup_elem(map, keys, key_sz, values, value_sz, flags);
+	if (!ASSERT_EQ(err, -ERANGE, "bpf_map__lookup_elem -ERANGE"))
+		goto out;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		/* clear value on all cpus */
+		values[0] = 0;
+		flags = BPF_F_ALL_CPUS;
+		for (i = 0; i < entries; i++) {
+			err = bpf_map__update_elem(map, keys + i * key_sz, key_sz, values,
+						   value_sz, flags);
+			if (!ASSERT_OK(err, "bpf_map__update_elem all_cpus"))
+				goto out;
+		}
+
+		/* update value on specified cpu */
+		for (i = 0; i < entries; i++) {
+			values[0] = value;
+			flags = (u64)cpu << 32 | BPF_F_CPU;
+			err = bpf_map__update_elem(map, keys + i * key_sz, key_sz, values,
+						   value_sz, flags);
+			if (!ASSERT_OK(err, "bpf_map__update_elem specified cpu"))
+				goto out;
+
+			/* lookup then check value on CPUs */
+			for (j = 0; j < nr_cpus; j++) {
+				flags = (u64)j << 32 | BPF_F_CPU;
+				err = bpf_map__lookup_elem(map, keys + i * key_sz, key_sz, values,
+							   value_sz, flags);
+				if (!ASSERT_OK(err, "bpf_map__lookup_elem specified cpu"))
+					goto out;
+				if (!ASSERT_EQ(values[0], j != cpu ? 0 : value,
+					       "bpf_map__lookup_elem value on specified cpu"))
+					goto out;
+			}
+		}
+	}
+
+	if (!test_batch)
+		goto out;
+
+	count = entries;
+	batch_opts.elem_flags = (u64)nr_cpus << 32 | BPF_F_CPU;
+	err = bpf_map_update_batch(map_fd, keys, values, &count, &batch_opts);
+	if (!ASSERT_EQ(err, -ERANGE, "bpf_map_update_batch -ERANGE"))
+		goto out;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		memset(values, 0, value_sz_total);
+
+		/* clear values across all CPUs */
+		count = entries;
+		batch_opts.elem_flags = BPF_F_ALL_CPUS;
+		err = bpf_map_update_batch(map_fd, keys, values, &count, &batch_opts);
+		if (!ASSERT_OK(err, "bpf_map_update_batch all_cpus"))
+			goto out;
+		if (!ASSERT_EQ(count, entries, "bpf_map_update_batch count"))
+			goto out;
+
+		/* update values on specified CPU */
+		for (i = 0; i < entries; i++)
+			values[i] = value;
+
+		count = entries;
+		batch_opts.elem_flags = (u64)cpu << 32 | BPF_F_CPU;
+		err = bpf_map_update_batch(map_fd, keys, values, &count, &batch_opts);
+		if (!ASSERT_OK(err, "bpf_map_update_batch specified cpu"))
+			goto out;
+		if (!ASSERT_EQ(count, entries, "bpf_map_update_batch count"))
+			goto out;
+
+		/* lookup values on specified CPU */
+		batch = 0;
+		count = entries;
+		memset(values, 0, entries * value_sz);
+		err = bpf_map_lookup_batch(map_fd, NULL, &batch, keys, values, &count, &batch_opts);
+		if (!ASSERT_TRUE(!err || err == -ENOENT, "bpf_map_lookup_batch specified cpu"))
+			goto out;
+		if (!ASSERT_EQ(count, entries, "bpf_map_lookup_batch count"))
+			goto out;
+
+		for (i = 0; i < entries; i++)
+			if (!ASSERT_EQ(values[i], value,
+				       "bpf_map_lookup_batch value on specified cpu"))
+				goto out;
+
+		/* lookup values from all CPUs */
+		batch = 0;
+		count = entries;
+		batch_opts.elem_flags = 0;
+		memset(values_percpu, 0, roundup(value_sz, 8) * nr_cpus * entries);
+		err = bpf_map_lookup_batch(map_fd, NULL, &batch, keys, values_percpu, &count,
+					   &batch_opts);
+		if (!ASSERT_TRUE(!err || err == -ENOENT, "bpf_map_lookup_batch all_cpus"))
+			goto out;
+		if (!ASSERT_EQ(count, entries, "bpf_map_lookup_batch count"))
+			goto out;
+
+		for (i = 0; i < entries; i++) {
+			values_row = (void *) values_percpu +
+				     roundup(value_sz, 8) * i * nr_cpus;
+			for (j = 0; j < nr_cpus; j++) {
+				v = *(u32 *) (values_row + roundup(value_sz, 8) * j);
+				if (!ASSERT_EQ(v, j != cpu ? 0 : value,
+					       "bpf_map_lookup_batch value all_cpus"))
+					goto out;
+			}
+		}
+	}
+
+out:
+	free(values_percpu);
+	free(values);
+}
+
+static void test_percpu_map_cpu_flag(enum bpf_map_type map_type)
+{
+	struct percpu_alloc_array *skel;
+	size_t key_sz = sizeof(int);
+	int *keys, nr_cpus, i, err;
+	struct bpf_map *map;
+	u32 max_entries;
+
+	nr_cpus = libbpf_num_possible_cpus();
+	if (!ASSERT_GT(nr_cpus, 0, "libbpf_num_possible_cpus"))
+		return;
+
+	max_entries = nr_cpus * 2;
+	keys = calloc(max_entries, key_sz);
+	if (!ASSERT_OK_PTR(keys, "calloc keys"))
+		return;
+
+	for (i = 0; i < max_entries; i++)
+		keys[i] = i;
+
+	skel = percpu_alloc_array__open();
+	if (!ASSERT_OK_PTR(skel, "percpu_alloc_array__open")) {
+		free(keys);
+		return;
+	}
+
+	map = skel->maps.percpu;
+	bpf_map__set_type(map, map_type);
+	bpf_map__set_max_entries(map, max_entries);
+
+	err = percpu_alloc_array__load(skel);
+	if (!ASSERT_OK(err, "test_percpu_alloc__load"))
+		goto out;
+
+	test_percpu_map_op_cpu_flag(map, keys, key_sz, nr_cpus, nr_cpus, true);
+out:
+	percpu_alloc_array__destroy(skel);
+	free(keys);
+}
+
+static void test_percpu_array_cpu_flag(void)
+{
+	test_percpu_map_cpu_flag(BPF_MAP_TYPE_PERCPU_ARRAY);
+}
+
+static void test_percpu_hash_cpu_flag(void)
+{
+	test_percpu_map_cpu_flag(BPF_MAP_TYPE_PERCPU_HASH);
+}
+
+static void test_lru_percpu_hash_cpu_flag(void)
+{
+	test_percpu_map_cpu_flag(BPF_MAP_TYPE_LRU_PERCPU_HASH);
+}
+
+static void test_percpu_cgroup_storage_cpu_flag(void)
+{
+	struct percpu_alloc_array *skel = NULL;
+	struct bpf_cgroup_storage_key key;
+	int cgroup, prog_fd, nr_cpus, err;
+	struct bpf_map *map;
+
+	nr_cpus = libbpf_num_possible_cpus();
+	if (!ASSERT_GT(nr_cpus, 0, "libbpf_num_possible_cpus"))
+		return;
+
+	err = setup_cgroup_environment();
+	if (!ASSERT_OK(err, "setup_cgroup_environment"))
+		return;
+
+	cgroup = create_and_get_cgroup("/cg_percpu");
+	if (!ASSERT_GE(cgroup, 0, "create_and_get_cgroup")) {
+		cleanup_cgroup_environment();
+		return;
+	}
+
+	err = join_cgroup("/cg_percpu");
+	if (!ASSERT_OK(err, "join_cgroup"))
+		goto out;
+
+	skel = percpu_alloc_array__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "percpu_alloc_array__open_and_load"))
+		goto out;
+
+	prog_fd = bpf_program__fd(skel->progs.cgroup_egress);
+	err = bpf_prog_attach(prog_fd, cgroup, BPF_CGROUP_INET_EGRESS, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach"))
+		goto out;
+
+	map = skel->maps.percpu_cgroup_storage;
+	err = bpf_map_get_next_key(bpf_map__fd(map), NULL, &key);
+	if (!ASSERT_OK(err, "bpf_map_get_next_key"))
+		goto out;
+
+	test_percpu_map_op_cpu_flag(map, &key, sizeof(key), 1, nr_cpus, false);
+out:
+	bpf_prog_detach2(-1, cgroup, BPF_CGROUP_INET_EGRESS);
+	close(cgroup);
+	cleanup_cgroup_environment();
+	percpu_alloc_array__destroy(skel);
+}
+
+static void test_map_op_cpu_flag(enum bpf_map_type map_type)
+{
+	u32 max_entries = 1, count = max_entries;
+	u64 flags, batch = 0, val = 0;
+	int err, map_fd, key = 0;
+	LIBBPF_OPTS(bpf_map_batch_opts, batch_opts);
+
+	map_fd = bpf_map_create(map_type, "test_cpu_flag", sizeof(int), sizeof(u64), max_entries,
+				NULL);
+	if (!ASSERT_GE(map_fd, 0, "bpf_map_create"))
+		return;
+
+	flags = BPF_F_ALL_CPUS;
+	err = bpf_map_update_elem(map_fd, &key, &val, flags);
+	ASSERT_ERR(err, "bpf_map_update_elem all_cpus");
+
+	batch_opts.elem_flags = BPF_F_ALL_CPUS;
+	err = bpf_map_update_batch(map_fd, &key, &val, &count, &batch_opts);
+	ASSERT_ERR(err, "bpf_map_update_batch all_cpus");
+
+	flags = BPF_F_CPU;
+	err = bpf_map_lookup_elem_flags(map_fd, &key, &val, flags);
+	ASSERT_ERR(err, "bpf_map_lookup_elem_flags cpu");
+
+	batch_opts.elem_flags = BPF_F_CPU;
+	err = bpf_map_lookup_batch(map_fd, NULL, &batch, &key, &val, &count, &batch_opts);
+	ASSERT_ERR(err, "bpf_map_lookup_batch cpu");
+
+	close(map_fd);
+}
+
+static void test_array_cpu_flag(void)
+{
+	test_map_op_cpu_flag(BPF_MAP_TYPE_ARRAY);
+}
+
+static void test_hash_cpu_flag(void)
+{
+	test_map_op_cpu_flag(BPF_MAP_TYPE_HASH);
+}
+
 void test_percpu_alloc(void)
 {
 	if (test__start_subtest("array"))
@@ -125,4 +448,16 @@ void test_percpu_alloc(void)
 		test_cgrp_local_storage();
 	if (test__start_subtest("failure_tests"))
 		test_failure();
+	if (test__start_subtest("cpu_flag_percpu_array"))
+		test_percpu_array_cpu_flag();
+	if (test__start_subtest("cpu_flag_percpu_hash"))
+		test_percpu_hash_cpu_flag();
+	if (test__start_subtest("cpu_flag_lru_percpu_hash"))
+		test_lru_percpu_hash_cpu_flag();
+	if (test__start_subtest("cpu_flag_percpu_cgroup_storage"))
+		test_percpu_cgroup_storage_cpu_flag();
+	if (test__start_subtest("cpu_flag_array"))
+		test_array_cpu_flag();
+	if (test__start_subtest("cpu_flag_hash"))
+		test_hash_cpu_flag();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
index 51544372f52e..41dfaaabb73f 100644
--- a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
+++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
@@ -101,9 +101,9 @@ static int resolve_symbols(void)
 	int type_id;
 	__u32 nr;
 
-	btf = btf__parse_elf("btf_data.bpf.o", NULL);
+	btf = btf__parse_raw("resolve_btfids.test.o.BTF");
 	if (CHECK(libbpf_get_error(btf), "resolve",
-		  "Failed to load BTF from btf_data.bpf.o\n"))
+		  "Failed to load BTF from resolve_btfids.test.o.BTF\n"))
 		return -1;
 
 	nr = btf__type_cnt(btf);
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_bypass_prot_mem.c b/tools/testing/selftests/bpf/prog_tests/sk_bypass_prot_mem.c
index e4940583924b..e2c867fd5244 100644
--- a/tools/testing/selftests/bpf/prog_tests/sk_bypass_prot_mem.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_bypass_prot_mem.c
@@ -5,9 +5,14 @@
 #include "sk_bypass_prot_mem.skel.h"
 #include "network_helpers.h"
 
+#ifndef PAGE_SIZE
+#include <unistd.h>
+#define PAGE_SIZE getpagesize()
+#endif
+
 #define NR_PAGES	32
 #define NR_SOCKETS	2
-#define BUF_TOTAL	(NR_PAGES * 4096 / NR_SOCKETS)
+#define BUF_TOTAL	(NR_PAGES * PAGE_SIZE / NR_SOCKETS)
 #define BUF_SINGLE	1024
 #define NR_SEND		(BUF_TOTAL / BUF_SINGLE)
 
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 1e3e4392dcca..256707e7d20d 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2020 Cloudflare
 #include <error.h>
-#include <netinet/tcp.h>
+#include <linux/tcp.h>
+#include <linux/socket.h>
 #include <sys/epoll.h>
 
 #include "test_progs.h"
@@ -22,6 +23,15 @@
 #define TCP_REPAIR_ON		1
 #define TCP_REPAIR_OFF_NO_WP	-1	/* Turn off without window probes */
 
+/**
+ * SOL_TCP is defined in <netinet/tcp.h> (glibc), but the copybuf_address
+ * field of tcp_zerocopy_receive is not yet included in older versions.
+ * This workaround remains necessary until the glibc update propagates.
+ */
+#ifndef SOL_TCP
+#define SOL_TCP 6
+#endif
+
 static int connected_socket_v4(void)
 {
 	struct sockaddr_in addr = {
@@ -536,13 +546,14 @@ out:
 }
 
 
-static void test_sockmap_skb_verdict_fionread(bool pass_prog)
+static void do_test_sockmap_skb_verdict_fionread(int sotype, bool pass_prog)
 {
 	int err, map, verdict, c0 = -1, c1 = -1, p0 = -1, p1 = -1;
 	int expected, zero = 0, sent, recvd, avail;
 	struct test_sockmap_pass_prog *pass = NULL;
 	struct test_sockmap_drop_prog *drop = NULL;
 	char buf[256] = "0123456789";
+	int split_len = sizeof(buf) / 2;
 
 	if (pass_prog) {
 		pass = test_sockmap_pass_prog__open_and_load();
@@ -550,7 +561,10 @@ static void test_sockmap_skb_verdict_fionread(bool pass_prog)
 			return;
 		verdict = bpf_program__fd(pass->progs.prog_skb_verdict);
 		map = bpf_map__fd(pass->maps.sock_map_rx);
-		expected = sizeof(buf);
+		if (sotype == SOCK_DGRAM)
+			expected = split_len; /* FIONREAD for UDP is different from TCP */
+		else
+			expected = sizeof(buf);
 	} else {
 		drop = test_sockmap_drop_prog__open_and_load();
 		if (!ASSERT_OK_PTR(drop, "open_and_load"))
@@ -566,7 +580,7 @@ static void test_sockmap_skb_verdict_fionread(bool pass_prog)
 	if (!ASSERT_OK(err, "bpf_prog_attach"))
 		goto out;
 
-	err = create_socket_pairs(AF_INET, SOCK_STREAM, &c0, &c1, &p0, &p1);
+	err = create_socket_pairs(AF_INET, sotype, &c0, &c1, &p0, &p1);
 	if (!ASSERT_OK(err, "create_socket_pairs()"))
 		goto out;
 
@@ -574,8 +588,9 @@ static void test_sockmap_skb_verdict_fionread(bool pass_prog)
 	if (!ASSERT_OK(err, "bpf_map_update_elem(c1)"))
 		goto out_close;
 
-	sent = xsend(p1, &buf, sizeof(buf), 0);
-	ASSERT_EQ(sent, sizeof(buf), "xsend(p0)");
+	sent = xsend(p1, &buf, split_len, 0);
+	sent += xsend(p1, &buf, sizeof(buf) - split_len, 0);
+	ASSERT_EQ(sent, sizeof(buf), "xsend(p1)");
 	err = ioctl(c1, FIONREAD, &avail);
 	ASSERT_OK(err, "ioctl(FIONREAD) error");
 	ASSERT_EQ(avail, expected, "ioctl(FIONREAD)");
@@ -597,6 +612,12 @@ out:
 		test_sockmap_drop_prog__destroy(drop);
 }
 
+static void test_sockmap_skb_verdict_fionread(bool pass_prog)
+{
+	do_test_sockmap_skb_verdict_fionread(SOCK_STREAM, pass_prog);
+	do_test_sockmap_skb_verdict_fionread(SOCK_DGRAM, pass_prog);
+}
+
 static void test_sockmap_skb_verdict_change_tail(void)
 {
 	struct test_sockmap_change_tail *skel;
@@ -1042,6 +1063,257 @@ close_map:
 	xclose(map);
 }
 
+/* it is used to reproduce WARNING */
+static void test_sockmap_zc(void)
+{
+	int map, err, sent, recvd, zero = 0, one = 1, on = 1;
+	char buf[10] = "0123456789", rcv[11], addr[100];
+	struct test_sockmap_pass_prog *skel = NULL;
+	int c0 = -1, p0 = -1, c1 = -1, p1 = -1;
+	struct tcp_zerocopy_receive zc;
+	socklen_t zc_len = sizeof(zc);
+	struct bpf_program *prog;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	if (create_socket_pairs(AF_INET, SOCK_STREAM, &c0, &c1, &p0, &p1))
+		goto end;
+
+	prog = skel->progs.prog_skb_verdict_ingress;
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	err = bpf_prog_attach(bpf_program__fd(prog), map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach"))
+		goto end;
+
+	err = bpf_map_update_elem(map, &zero, &p0, BPF_ANY);
+	if (!ASSERT_OK(err, "bpf_map_update_elem"))
+		goto end;
+
+	err = bpf_map_update_elem(map, &one, &p1, BPF_ANY);
+	if (!ASSERT_OK(err, "bpf_map_update_elem"))
+		goto end;
+
+	sent = xsend(c0, buf, sizeof(buf), 0);
+	if (!ASSERT_EQ(sent, sizeof(buf), "xsend"))
+		goto end;
+
+	/* trigger tcp_bpf_recvmsg_parser and inc copied_seq of p1 */
+	recvd = recv_timeout(p1, rcv, sizeof(rcv), MSG_DONTWAIT, 1);
+	if (!ASSERT_EQ(recvd, sent, "recv_timeout(p1)"))
+		goto end;
+
+	/* uninstall sockmap of p1 */
+	bpf_map_delete_elem(map, &one);
+
+	/* trigger tcp stack and the rcv_nxt of p1 is less than copied_seq */
+	sent = xsend(c1, buf, sizeof(buf) - 1, 0);
+	if (!ASSERT_EQ(sent, sizeof(buf) - 1, "xsend"))
+		goto end;
+
+	err = setsockopt(p1, SOL_SOCKET, SO_ZEROCOPY, &on, sizeof(on));
+	if (!ASSERT_OK(err, "setsockopt"))
+		goto end;
+
+	memset(&zc, 0, sizeof(zc));
+	zc.copybuf_address = (__u64)((unsigned long)addr);
+	zc.copybuf_len = sizeof(addr);
+
+	err = getsockopt(p1, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, &zc, &zc_len);
+	if (!ASSERT_OK(err, "getsockopt"))
+		goto end;
+
+end:
+	if (c0 >= 0)
+		close(c0);
+	if (p0 >= 0)
+		close(p0);
+	if (c1 >= 0)
+		close(c1);
+	if (p1 >= 0)
+		close(p1);
+	test_sockmap_pass_prog__destroy(skel);
+}
+
+/* it is used to check whether copied_seq of sk is correct */
+static void test_sockmap_copied_seq(bool strp)
+{
+	int i, map, err, sent, recvd, zero = 0, one = 1;
+	struct test_sockmap_pass_prog *skel = NULL;
+	int c0 = -1, p0 = -1, c1 = -1, p1 = -1;
+	char buf[10] = "0123456789", rcv[11];
+	struct bpf_program *prog;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	if (create_socket_pairs(AF_INET, SOCK_STREAM, &c0, &c1, &p0, &p1))
+		goto end;
+
+	prog = skel->progs.prog_skb_verdict_ingress;
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	err = bpf_prog_attach(bpf_program__fd(prog), map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach verdict"))
+		goto end;
+
+	if (strp) {
+		prog = skel->progs.prog_skb_verdict_ingress_strp;
+		err = bpf_prog_attach(bpf_program__fd(prog), map, BPF_SK_SKB_STREAM_PARSER, 0);
+		if (!ASSERT_OK(err, "bpf_prog_attach parser"))
+			goto end;
+	}
+
+	err = bpf_map_update_elem(map, &zero, &p0, BPF_ANY);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p0)"))
+		goto end;
+
+	err = bpf_map_update_elem(map, &one, &p1, BPF_ANY);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p1)"))
+		goto end;
+
+	/* just trigger sockamp: data sent by c0 will be received by p1 */
+	sent = xsend(c0, buf, sizeof(buf), 0);
+	if (!ASSERT_EQ(sent, sizeof(buf), "xsend(c0), bpf"))
+		goto end;
+
+	/* do partial read */
+	recvd = recv_timeout(p1, rcv, 1, MSG_DONTWAIT, 1);
+	recvd += recv_timeout(p1, rcv + 1, sizeof(rcv) - 1, MSG_DONTWAIT, 1);
+	if (!ASSERT_EQ(recvd, sent, "recv_timeout(p1), bpf") ||
+	    !ASSERT_OK(memcmp(buf, rcv, recvd), "data mismatch"))
+		goto end;
+
+	/* uninstall sockmap of p1 and p0 */
+	err = bpf_map_delete_elem(map, &one);
+	if (!ASSERT_OK(err, "bpf_map_delete_elem(1)"))
+		goto end;
+
+	err = bpf_map_delete_elem(map, &zero);
+	if (!ASSERT_OK(err, "bpf_map_delete_elem(0)"))
+		goto end;
+
+	/* now all sockets become plain socket, they should still work */
+	for (i = 0; i < 5; i++) {
+		/* test copied_seq of p1 by running tcp native stack */
+		sent = xsend(c1, buf, sizeof(buf), 0);
+		if (!ASSERT_EQ(sent, sizeof(buf), "xsend(c1), native"))
+			goto end;
+
+		recvd = recv(p1, rcv, sizeof(rcv), MSG_DONTWAIT);
+		if (!ASSERT_EQ(recvd, sent, "recv_timeout(p1), native"))
+			goto end;
+
+		/* p0 previously redirected skb to p1, we also check copied_seq of p0 */
+		sent = xsend(c0, buf, sizeof(buf), 0);
+		if (!ASSERT_EQ(sent, sizeof(buf), "xsend(c0), native"))
+			goto end;
+
+		recvd = recv(p0, rcv, sizeof(rcv), MSG_DONTWAIT);
+		if (!ASSERT_EQ(recvd, sent, "recv_timeout(p0), native"))
+			goto end;
+	}
+
+end:
+	if (c0 >= 0)
+		close(c0);
+	if (p0 >= 0)
+		close(p0);
+	if (c1 >= 0)
+		close(c1);
+	if (p1 >= 0)
+		close(p1);
+	test_sockmap_pass_prog__destroy(skel);
+}
+
+/* Wait until FIONREAD returns the expected value or timeout */
+static int wait_for_fionread(int fd, int expected, unsigned int timeout_ms)
+{
+	unsigned int elapsed = 0;
+	int avail = 0;
+
+	while (elapsed < timeout_ms) {
+		if (ioctl(fd, FIONREAD, &avail) < 0)
+			return -errno;
+		if (avail >= expected)
+			return avail;
+		usleep(1000);
+		elapsed++;
+	}
+	return avail;
+}
+
+/* it is used to send data to via native stack and BPF redirecting */
+static void test_sockmap_multi_channels(int sotype)
+{
+	int map, err, sent, recvd, zero = 0, one = 1, avail = 0, expected;
+	struct test_sockmap_pass_prog *skel = NULL;
+	int c0 = -1, p0 = -1, c1 = -1, p1 = -1;
+	char buf[10] = "0123456789", rcv[11];
+	struct bpf_program *prog;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	err = create_socket_pairs(AF_INET, sotype, &c0, &c1, &p0, &p1);
+	if (err)
+		goto end;
+
+	prog = skel->progs.prog_skb_verdict_ingress;
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	err = bpf_prog_attach(bpf_program__fd(prog), map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach verdict"))
+		goto end;
+
+	err = bpf_map_update_elem(map, &zero, &p0, BPF_ANY);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p0)"))
+		goto end;
+
+	err = bpf_map_update_elem(map, &one, &p1, BPF_ANY);
+	if (!ASSERT_OK(err, "bpf_map_update_elem"))
+		goto end;
+
+	/* send data to p1 via native stack */
+	sent = xsend(c1, buf, 2, 0);
+	if (!ASSERT_EQ(sent, 2, "xsend(2)"))
+		goto end;
+
+	avail = wait_for_fionread(p1, 2, IO_TIMEOUT_SEC);
+	ASSERT_EQ(avail, 2, "ioctl(FIONREAD) partial return");
+
+	/* send data to p1 via bpf redirecting */
+	sent = xsend(c0, buf + 2, sizeof(buf) - 2, 0);
+	if (!ASSERT_EQ(sent, sizeof(buf) - 2, "xsend(remain-data)"))
+		goto end;
+
+	/* Poll FIONREAD until expected bytes arrive, poll_read() is unreliable
+	 * here since it may return immediately if prior data is already queued.
+	 */
+	expected = sotype == SOCK_DGRAM ? 2 : sizeof(buf);
+	avail = wait_for_fionread(p1, expected, IO_TIMEOUT_SEC);
+	ASSERT_EQ(avail, expected, "ioctl(FIONREAD) full return");
+
+	recvd = recv_timeout(p1, rcv, sizeof(rcv), MSG_DONTWAIT, 1);
+	if (!ASSERT_EQ(recvd, sizeof(buf), "recv_timeout(p1)") ||
+	    !ASSERT_OK(memcmp(buf, rcv, recvd), "data mismatch"))
+		goto end;
+end:
+	if (c0 >= 0)
+		close(c0);
+	if (p0 >= 0)
+		close(p0);
+	if (c1 >= 0)
+		close(c1);
+	if (p1 >= 0)
+		close(p1);
+	test_sockmap_pass_prog__destroy(skel);
+}
+
 void test_sockmap_basic(void)
 {
 	if (test__start_subtest("sockmap create_update_free"))
@@ -1108,4 +1380,14 @@ void test_sockmap_basic(void)
 		test_sockmap_skb_verdict_vsock_poll();
 	if (test__start_subtest("sockmap vsock unconnected"))
 		test_sockmap_vsock_unconnected();
+	if (test__start_subtest("sockmap with zc"))
+		test_sockmap_zc();
+	if (test__start_subtest("sockmap recover"))
+		test_sockmap_copied_seq(false);
+	if (test__start_subtest("sockmap recover with strp"))
+		test_sockmap_copied_seq(true);
+	if (test__start_subtest("sockmap tcp multi channels"))
+		test_sockmap_multi_channels(SOCK_STREAM);
+	if (test__start_subtest("sockmap udp multi channels"))
+		test_sockmap_multi_channels(SOCK_DGRAM);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c
index c9efdd2a5b18..da42b00e3d1f 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c
@@ -74,11 +74,20 @@ static void test_stacktrace_ips_kprobe_multi(bool retprobe)
 
 	load_kallsyms();
 
-	check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 4,
-			     ksym_get_addr("bpf_testmod_stacktrace_test_3"),
-			     ksym_get_addr("bpf_testmod_stacktrace_test_2"),
-			     ksym_get_addr("bpf_testmod_stacktrace_test_1"),
-			     ksym_get_addr("bpf_testmod_test_read"));
+	if (retprobe) {
+		check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 4,
+				     ksym_get_addr("bpf_testmod_stacktrace_test_3"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_2"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_1"),
+				     ksym_get_addr("bpf_testmod_test_read"));
+	} else {
+		check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 5,
+				     ksym_get_addr("bpf_testmod_stacktrace_test"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_3"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_2"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_1"),
+				     ksym_get_addr("bpf_testmod_test_read"));
+	}
 
 cleanup:
 	stacktrace_ips__destroy(skel);
@@ -128,6 +137,99 @@ cleanup:
 	stacktrace_ips__destroy(skel);
 }
 
+static void test_stacktrace_ips_kprobe(bool retprobe)
+{
+	LIBBPF_OPTS(bpf_kprobe_opts, opts,
+		.retprobe = retprobe
+	);
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct stacktrace_ips *skel;
+
+	skel = stacktrace_ips__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "stacktrace_ips__open_and_load"))
+		return;
+
+	if (!skel->kconfig->CONFIG_UNWINDER_ORC) {
+		test__skip();
+		goto cleanup;
+	}
+
+	skel->links.kprobe_test = bpf_program__attach_kprobe_opts(
+						skel->progs.kprobe_test,
+						"bpf_testmod_stacktrace_test", &opts);
+	if (!ASSERT_OK_PTR(skel->links.kprobe_test, "bpf_program__attach_kprobe_opts"))
+		goto cleanup;
+
+	trigger_module_test_read(1);
+
+	load_kallsyms();
+
+	if (retprobe) {
+		check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 4,
+				     ksym_get_addr("bpf_testmod_stacktrace_test_3"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_2"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_1"),
+				     ksym_get_addr("bpf_testmod_test_read"));
+	} else {
+		check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 5,
+				     ksym_get_addr("bpf_testmod_stacktrace_test"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_3"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_2"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_1"),
+				     ksym_get_addr("bpf_testmod_test_read"));
+	}
+
+cleanup:
+	stacktrace_ips__destroy(skel);
+}
+
+static void test_stacktrace_ips_trampoline(bool retprobe)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct stacktrace_ips *skel;
+
+	skel = stacktrace_ips__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "stacktrace_ips__open_and_load"))
+		return;
+
+	if (!skel->kconfig->CONFIG_UNWINDER_ORC) {
+		test__skip();
+		goto cleanup;
+	}
+
+	if (retprobe) {
+		skel->links.fexit_test = bpf_program__attach_trace(skel->progs.fexit_test);
+		if (!ASSERT_OK_PTR(skel->links.fexit_test, "bpf_program__attach_trace"))
+			goto cleanup;
+	} else {
+		skel->links.fentry_test = bpf_program__attach_trace(skel->progs.fentry_test);
+		if (!ASSERT_OK_PTR(skel->links.fentry_test, "bpf_program__attach_trace"))
+			goto cleanup;
+	}
+
+	trigger_module_test_read(1);
+
+	load_kallsyms();
+
+	if (retprobe) {
+		check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 4,
+				     ksym_get_addr("bpf_testmod_stacktrace_test_3"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_2"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_1"),
+				     ksym_get_addr("bpf_testmod_test_read"));
+	} else {
+		check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 5,
+				     ksym_get_addr("bpf_testmod_stacktrace_test"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_3"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_2"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_1"),
+				     ksym_get_addr("bpf_testmod_test_read"));
+	}
+
+cleanup:
+	stacktrace_ips__destroy(skel);
+}
+
 static void __test_stacktrace_ips(void)
 {
 	if (test__start_subtest("kprobe_multi"))
@@ -136,6 +238,14 @@ static void __test_stacktrace_ips(void)
 		test_stacktrace_ips_kprobe_multi(true);
 	if (test__start_subtest("raw_tp"))
 		test_stacktrace_ips_raw_tp();
+	if (test__start_subtest("kprobe"))
+		test_stacktrace_ips_kprobe(false);
+	if (test__start_subtest("kretprobe"))
+		test_stacktrace_ips_kprobe(true);
+	if (test__start_subtest("fentry"))
+		test_stacktrace_ips_trampoline(false);
+	if (test__start_subtest("fexit"))
+		test_stacktrace_ips_trampoline(true);
 }
 #else
 static void __test_stacktrace_ips(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c b/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c
index 0f3bf594e7a5..300032a19445 100644
--- a/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c
+++ b/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c
@@ -9,6 +9,7 @@
 static const char * const test_cases[] = {
 	"strcmp",
 	"strcasecmp",
+	"strncasecmp",
 	"strchr",
 	"strchrnul",
 	"strnchr",
diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index 0ab36503c3b2..7d534fde0af9 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -8,6 +8,7 @@
 #include "tailcall_freplace.skel.h"
 #include "tc_bpf2bpf.skel.h"
 #include "tailcall_fail.skel.h"
+#include "tailcall_sleepable.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
@@ -1653,6 +1654,77 @@ static void test_tailcall_failure()
 	RUN_TESTS(tailcall_fail);
 }
 
+noinline void uprobe_sleepable_trigger(void)
+{
+	asm volatile ("");
+}
+
+static void test_tailcall_sleepable(void)
+{
+	LIBBPF_OPTS(bpf_uprobe_opts, opts);
+	struct tailcall_sleepable *skel;
+	int prog_fd, map_fd;
+	int err, key;
+
+	skel = tailcall_sleepable__open();
+	if (!ASSERT_OK_PTR(skel, "tailcall_sleepable__open"))
+		return;
+
+	/*
+	 * Test that we can't load uprobe_normal and uprobe_sleepable_1,
+	 * because they share tailcall map.
+	 */
+	bpf_program__set_autoload(skel->progs.uprobe_normal, true);
+	bpf_program__set_autoload(skel->progs.uprobe_sleepable_1, true);
+
+	err = tailcall_sleepable__load(skel);
+	if (!ASSERT_ERR(err, "tailcall_sleepable__load"))
+		goto out;
+
+	tailcall_sleepable__destroy(skel);
+
+	/*
+	 * Test that we can tail call from sleepable to sleepable program.
+	 */
+	skel = tailcall_sleepable__open();
+	if (!ASSERT_OK_PTR(skel, "tailcall_sleepable__open"))
+		return;
+
+	bpf_program__set_autoload(skel->progs.uprobe_sleepable_1, true);
+	bpf_program__set_autoload(skel->progs.uprobe_sleepable_2, true);
+
+	err = tailcall_sleepable__load(skel);
+	if (!ASSERT_OK(err, "tailcall_sleepable__load"))
+		goto out;
+
+	/* Add sleepable uprobe_sleepable_2 to jmp_table[0]. */
+	key = 0;
+	prog_fd = bpf_program__fd(skel->progs.uprobe_sleepable_2);
+	map_fd = bpf_map__fd(skel->maps.jmp_table);
+	err = bpf_map_update_elem(map_fd, &key, &prog_fd, BPF_ANY);
+	if (!ASSERT_OK(err, "update jmp_table"))
+		goto out;
+
+	skel->bss->my_pid = getpid();
+
+	/* Attach uprobe_sleepable_1 to uprobe_sleepable_trigger and hit it.  */
+	opts.func_name = "uprobe_sleepable_trigger";
+	skel->links.uprobe_sleepable_1 = bpf_program__attach_uprobe_opts(
+						skel->progs.uprobe_sleepable_1,
+						-1,
+						"/proc/self/exe",
+						0 /* offset */,
+						&opts);
+	if (!ASSERT_OK_PTR(skel->links.uprobe_sleepable_1, "bpf_program__attach_uprobe_opts"))
+		goto out;
+
+	uprobe_sleepable_trigger();
+	ASSERT_EQ(skel->bss->executed, 1, "executed");
+
+out:
+	tailcall_sleepable__destroy(skel);
+}
+
 void test_tailcalls(void)
 {
 	if (test__start_subtest("tailcall_1"))
@@ -1707,4 +1779,6 @@ void test_tailcalls(void)
 		test_tailcall_bpf2bpf_freplace();
 	if (test__start_subtest("tailcall_failure"))
 		test_tailcall_failure();
+	if (test__start_subtest("tailcall_sleepable"))
+		test_tailcall_sleepable();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_data.h b/tools/testing/selftests/bpf/prog_tests/task_local_data.h
index 2de38776a2d4..0f86b9275cf9 100644
--- a/tools/testing/selftests/bpf/prog_tests/task_local_data.h
+++ b/tools/testing/selftests/bpf/prog_tests/task_local_data.h
@@ -94,7 +94,7 @@ struct tld_metadata {
 };
 
 struct tld_meta_u {
-	_Atomic __u8 cnt;
+	_Atomic __u16 cnt;
 	__u16 size;
 	struct tld_metadata metadata[];
 };
@@ -217,7 +217,7 @@ out:
 static tld_key_t __tld_create_key(const char *name, size_t size, bool dyn_data)
 {
 	int err, i, sz, off = 0;
-	__u8 cnt;
+	__u16 cnt;
 
 	if (!TLD_READ_ONCE(tld_meta_p)) {
 		err = __tld_init_meta_p();
diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
index 42e822ea352f..7bee33797c71 100644
--- a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
+++ b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
@@ -112,24 +112,24 @@ static void test_recursion(void)
 	task_ls_recursion__detach(skel);
 
 	/* Refer to the comment in BPF_PROG(on_update) for
-	 * the explanation on the value 201 and 100.
+	 * the explanation on the value 200 and 1.
 	 */
 	map_fd = bpf_map__fd(skel->maps.map_a);
 	err = bpf_map_lookup_elem(map_fd, &task_fd, &value);
 	ASSERT_OK(err, "lookup map_a");
-	ASSERT_EQ(value, 201, "map_a value");
-	ASSERT_EQ(skel->bss->nr_del_errs, 1, "bpf_task_storage_delete busy");
+	ASSERT_EQ(value, 200, "map_a value");
+	ASSERT_EQ(skel->bss->nr_del_errs, 0, "bpf_task_storage_delete busy");
 
 	map_fd = bpf_map__fd(skel->maps.map_b);
 	err = bpf_map_lookup_elem(map_fd, &task_fd, &value);
 	ASSERT_OK(err, "lookup map_b");
-	ASSERT_EQ(value, 100, "map_b value");
+	ASSERT_EQ(value, 1, "map_b value");
 
 	prog_fd = bpf_program__fd(skel->progs.on_update);
 	memset(&info, 0, sizeof(info));
 	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
 	ASSERT_OK(err, "get prog info");
-	ASSERT_EQ(info.recursion_misses, 0, "on_update prog recursion");
+	ASSERT_EQ(info.recursion_misses, 2, "on_update prog recursion");
 
 	prog_fd = bpf_program__fd(skel->progs.on_enter);
 	memset(&info, 0, sizeof(info));
diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_assoc.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_assoc.c
new file mode 100644
index 000000000000..461ded722351
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_assoc.c
@@ -0,0 +1,191 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "struct_ops_assoc.skel.h"
+#include "struct_ops_assoc_reuse.skel.h"
+#include "struct_ops_assoc_in_timer.skel.h"
+
+static void test_st_ops_assoc(void)
+{
+	struct struct_ops_assoc *skel = NULL;
+	int err, pid;
+
+	skel = struct_ops_assoc__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_assoc__open"))
+		goto out;
+
+	/* cannot explicitly associate struct_ops program */
+	err = bpf_program__assoc_struct_ops(skel->progs.test_1_a,
+					    skel->maps.st_ops_map_a, NULL);
+	ASSERT_ERR(err, "bpf_program__assoc_struct_ops(test_1_a, st_ops_map_a)");
+
+	err = bpf_program__assoc_struct_ops(skel->progs.syscall_prog_a,
+					    skel->maps.st_ops_map_a, NULL);
+	ASSERT_OK(err, "bpf_program__assoc_struct_ops(syscall_prog_a, st_ops_map_a)");
+
+	err = bpf_program__assoc_struct_ops(skel->progs.sys_enter_prog_a,
+					    skel->maps.st_ops_map_a, NULL);
+	ASSERT_OK(err, "bpf_program__assoc_struct_ops(sys_enter_prog_a, st_ops_map_a)");
+
+	err = bpf_program__assoc_struct_ops(skel->progs.syscall_prog_b,
+					    skel->maps.st_ops_map_b, NULL);
+	ASSERT_OK(err, "bpf_program__assoc_struct_ops(syscall_prog_b, st_ops_map_b)");
+
+	err = bpf_program__assoc_struct_ops(skel->progs.sys_enter_prog_b,
+					    skel->maps.st_ops_map_b, NULL);
+	ASSERT_OK(err, "bpf_program__assoc_struct_ops(sys_enter_prog_b, st_ops_map_b)");
+
+	/* sys_enter_prog_a already associated with map_a */
+	err = bpf_program__assoc_struct_ops(skel->progs.sys_enter_prog_a,
+					    skel->maps.st_ops_map_b, NULL);
+	ASSERT_ERR(err, "bpf_program__assoc_struct_ops(sys_enter_prog_a, st_ops_map_b)");
+
+	err = struct_ops_assoc__attach(skel);
+	if (!ASSERT_OK(err, "struct_ops_assoc__attach"))
+		goto out;
+
+	/* run tracing prog that calls .test_1 and checks return */
+	pid = getpid();
+	skel->bss->test_pid = pid;
+	sys_gettid();
+	skel->bss->test_pid = 0;
+
+	ASSERT_EQ(skel->bss->test_err_a, 0, "skel->bss->test_err_a");
+	ASSERT_EQ(skel->bss->test_err_b, 0, "skel->bss->test_err_b");
+
+	/* run syscall_prog that calls .test_1 and checks return */
+	err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.syscall_prog_a), NULL);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+
+	err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.syscall_prog_b), NULL);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+
+	ASSERT_EQ(skel->bss->test_err_a, 0, "skel->bss->test_err_a");
+	ASSERT_EQ(skel->bss->test_err_b, 0, "skel->bss->test_err_b");
+
+out:
+	struct_ops_assoc__destroy(skel);
+}
+
+static void test_st_ops_assoc_reuse(void)
+{
+	struct struct_ops_assoc_reuse *skel = NULL;
+	int err;
+
+	skel = struct_ops_assoc_reuse__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_assoc_reuse__open"))
+		goto out;
+
+	err = bpf_program__assoc_struct_ops(skel->progs.syscall_prog_a,
+					    skel->maps.st_ops_map_a, NULL);
+	ASSERT_OK(err, "bpf_program__assoc_struct_ops(syscall_prog_a, st_ops_map_a)");
+
+	err = bpf_program__assoc_struct_ops(skel->progs.syscall_prog_b,
+					    skel->maps.st_ops_map_b, NULL);
+	ASSERT_OK(err, "bpf_program__assoc_struct_ops(syscall_prog_b, st_ops_map_b)");
+
+	err = struct_ops_assoc_reuse__attach(skel);
+	if (!ASSERT_OK(err, "struct_ops_assoc__attach"))
+		goto out;
+
+	/* run syscall_prog that calls .test_1 and checks return */
+	err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.syscall_prog_a), NULL);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+
+	err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.syscall_prog_b), NULL);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+
+	ASSERT_EQ(skel->bss->test_err_a, 0, "skel->bss->test_err_a");
+	ASSERT_EQ(skel->bss->test_err_b, 0, "skel->bss->test_err_b");
+
+out:
+	struct_ops_assoc_reuse__destroy(skel);
+}
+
+static void test_st_ops_assoc_in_timer(void)
+{
+	struct struct_ops_assoc_in_timer *skel = NULL;
+	int err;
+
+	skel = struct_ops_assoc_in_timer__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_assoc_in_timer__open"))
+		goto out;
+
+	err = bpf_program__assoc_struct_ops(skel->progs.syscall_prog,
+					    skel->maps.st_ops_map, NULL);
+	ASSERT_OK(err, "bpf_program__assoc_struct_ops");
+
+	err = struct_ops_assoc_in_timer__attach(skel);
+	if (!ASSERT_OK(err, "struct_ops_assoc__attach"))
+		goto out;
+
+	/*
+	 * Run .test_1 by calling kfunc bpf_kfunc_multi_st_ops_test_1_prog_arg() and checks
+	 * the return value. .test_1 will also schedule timer_cb that runs .test_1 again
+	 * immediately.
+	 */
+	err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.syscall_prog), NULL);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+
+	/* Check the return of the kfunc after timer_cb runs */
+	while (!READ_ONCE(skel->bss->timer_cb_run))
+		sched_yield();
+	ASSERT_EQ(skel->bss->timer_test_1_ret, 1234, "skel->bss->timer_test_1_ret");
+	ASSERT_EQ(skel->bss->test_err, 0, "skel->bss->test_err_a");
+out:
+	struct_ops_assoc_in_timer__destroy(skel);
+}
+
+static void test_st_ops_assoc_in_timer_no_uref(void)
+{
+	struct struct_ops_assoc_in_timer *skel = NULL;
+	struct bpf_link *link;
+	int err;
+
+	skel = struct_ops_assoc_in_timer__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_assoc_in_timer__open"))
+		goto out;
+
+	err = bpf_program__assoc_struct_ops(skel->progs.syscall_prog,
+					    skel->maps.st_ops_map, NULL);
+	ASSERT_OK(err, "bpf_program__assoc_struct_ops");
+
+	link = bpf_map__attach_struct_ops(skel->maps.st_ops_map);
+	if (!ASSERT_OK_PTR(link, "bpf_map__attach_struct_ops"))
+		goto out;
+
+	/*
+	 * Run .test_1 by calling kfunc bpf_kfunc_multi_st_ops_test_1_prog_arg() and checks
+	 * the return value. .test_1 will also schedule timer_cb that runs .test_1 again.
+	 * timer_cb will run 500ms after syscall_prog runs, when the user space no longer
+	 * holds a reference to st_ops_map.
+	 */
+	skel->bss->timer_ns = 500000000;
+	err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.syscall_prog), NULL);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+
+	/* Detach and close struct_ops map to cause it to be freed */
+	bpf_link__destroy(link);
+	close(bpf_program__fd(skel->progs.syscall_prog));
+	close(bpf_map__fd(skel->maps.st_ops_map));
+
+	/* Check the return of the kfunc after timer_cb runs */
+	while (!READ_ONCE(skel->bss->timer_cb_run))
+		sched_yield();
+	ASSERT_EQ(skel->bss->timer_test_1_ret, -1, "skel->bss->timer_test_1_ret");
+	ASSERT_EQ(skel->bss->test_err, 0, "skel->bss->test_err_a");
+out:
+	struct_ops_assoc_in_timer__destroy(skel);
+}
+
+void test_struct_ops_assoc(void)
+{
+	if (test__start_subtest("st_ops_assoc"))
+		test_st_ops_assoc();
+	if (test__start_subtest("st_ops_assoc_reuse"))
+		test_st_ops_assoc_reuse();
+	if (test__start_subtest("st_ops_assoc_in_timer"))
+		test_st_ops_assoc_in_timer();
+	if (test__start_subtest("st_ops_assoc_in_timer_no_uref"))
+		test_st_ops_assoc_in_timer_no_uref();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_task_local_data.c b/tools/testing/selftests/bpf/prog_tests/test_task_local_data.c
index 9fd6306b455c..9556ad3d986f 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_task_local_data.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_task_local_data.c
@@ -4,7 +4,7 @@
 #include <test_progs.h>
 
 #define TLD_FREE_DATA_ON_THREAD_EXIT
-#define TLD_DYN_DATA_SIZE 4096
+#define TLD_DYN_DATA_SIZE (getpagesize() - 8)
 #include "task_local_data.h"
 
 struct test_tld_struct {
diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.c b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
index 5af28f359cfd..bab4a31621c7 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_xsk.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
@@ -433,7 +433,7 @@ static u32 pkt_nb_frags(u32 frame_size, struct pkt_stream *pkt_stream, struct pk
 	}
 
 	/* Search for the end of the packet in verbatim mode */
-	if (!pkt_continues(pkt->options))
+	if (!pkt_continues(pkt->options) || !pkt->valid)
 		return nb_frags;
 
 	next_frag = pkt_stream->current_pkt_nb;
@@ -1090,6 +1090,8 @@ static int __receive_pkts(struct test_spec *test, struct xsk_socket_info *xsk)
 			xsk_ring_prod__cancel(&umem->fq, nb_frags);
 		}
 		frags_processed -= nb_frags;
+		pkt_stream_cancel(pkt_stream);
+		pkts_sent--;
 	}
 
 	if (ifobj->use_fill_ring)
diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c
index 34f9ccce2602..09ff21e1ad2f 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer.c
@@ -1,12 +1,27 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2021 Facebook */
+#include <sched.h>
 #include <test_progs.h>
+#include <linux/perf_event.h>
+#include <sys/syscall.h>
 #include "timer.skel.h"
 #include "timer_failure.skel.h"
 #include "timer_interrupt.skel.h"
 
 #define NUM_THR 8
 
+static int perf_event_open(__u32 type, __u64 config, int pid, int cpu)
+{
+	struct perf_event_attr attr = {
+		.type = type,
+		.config = config,
+		.size = sizeof(struct perf_event_attr),
+		.sample_period = 10000,
+	};
+
+	return syscall(__NR_perf_event_open, &attr, pid, cpu, -1, 0);
+}
+
 static void *spin_lock_thread(void *arg)
 {
 	int i, err, prog_fd = *(int *)arg;
@@ -22,13 +37,174 @@ static void *spin_lock_thread(void *arg)
 	pthread_exit(arg);
 }
 
-static int timer(struct timer *timer_skel)
+
+static int timer_stress_runner(struct timer *timer_skel, bool async_cancel)
 {
-	int i, err, prog_fd;
+	int i, err = 1, prog_fd;
 	LIBBPF_OPTS(bpf_test_run_opts, topts);
 	pthread_t thread_id[NUM_THR];
 	void *ret;
 
+	timer_skel->bss->async_cancel = async_cancel;
+	prog_fd = bpf_program__fd(timer_skel->progs.race);
+	for (i = 0; i < NUM_THR; i++) {
+		err = pthread_create(&thread_id[i], NULL,
+				     &spin_lock_thread, &prog_fd);
+		if (!ASSERT_OK(err, "pthread_create"))
+			break;
+	}
+
+	while (i) {
+		err = pthread_join(thread_id[--i], &ret);
+		if (ASSERT_OK(err, "pthread_join"))
+			ASSERT_EQ(ret, (void *)&prog_fd, "pthread_join");
+	}
+	return err;
+}
+
+static int timer_stress(struct timer *timer_skel)
+{
+	return timer_stress_runner(timer_skel, false);
+}
+
+static int timer_stress_async_cancel(struct timer *timer_skel)
+{
+	return timer_stress_runner(timer_skel, true);
+}
+
+static void *nmi_cpu_worker(void *arg)
+{
+	volatile __u64 num = 1;
+	int i;
+
+	for (i = 0; i < 500000000; ++i)
+		num *= (i % 7) + 1;
+	(void)num;
+
+	return NULL;
+}
+
+static int run_nmi_test(struct timer *timer_skel, struct bpf_program *prog)
+{
+	struct bpf_link *link = NULL;
+	int pe_fd = -1, pipefd[2] = {-1, -1}, pid = 0, status;
+	char buf = 0;
+	int ret = -1;
+
+	if (!ASSERT_OK(pipe(pipefd), "pipe"))
+		goto cleanup;
+
+	pid = fork();
+	if (pid == 0) {
+		/* Child: spawn multiple threads to consume multiple CPUs */
+		pthread_t threads[NUM_THR];
+		int i;
+
+		close(pipefd[1]);
+		read(pipefd[0], &buf, 1);
+		close(pipefd[0]);
+
+		for (i = 0; i < NUM_THR; i++)
+			pthread_create(&threads[i], NULL, nmi_cpu_worker, NULL);
+		for (i = 0; i < NUM_THR; i++)
+			pthread_join(threads[i], NULL);
+		exit(0);
+	}
+
+	if (!ASSERT_GE(pid, 0, "fork"))
+		goto cleanup;
+
+	/* Open perf event for child process across all CPUs */
+	pe_fd = perf_event_open(PERF_TYPE_HARDWARE,
+				PERF_COUNT_HW_CPU_CYCLES,
+				pid,  /* measure child process */
+				-1);  /* on any CPU */
+	if (pe_fd < 0) {
+		if (errno == ENOENT || errno == EOPNOTSUPP) {
+			printf("SKIP:no PERF_COUNT_HW_CPU_CYCLES\n");
+			test__skip();
+			ret = EOPNOTSUPP;
+			goto cleanup;
+		}
+		ASSERT_GE(pe_fd, 0, "perf_event_open");
+		goto cleanup;
+	}
+
+	link = bpf_program__attach_perf_event(prog, pe_fd);
+	if (!ASSERT_OK_PTR(link, "attach_perf_event"))
+		goto cleanup;
+	pe_fd = -1;  /* Ownership transferred to link */
+
+	/* Signal child to start CPU work */
+	close(pipefd[0]);
+	pipefd[0] = -1;
+	write(pipefd[1], &buf, 1);
+	close(pipefd[1]);
+	pipefd[1] = -1;
+
+	waitpid(pid, &status, 0);
+	pid = 0;
+
+	/* Verify NMI context was hit */
+	ASSERT_GT(timer_skel->bss->test_hits, 0, "test_hits");
+	ret = 0;
+
+cleanup:
+	bpf_link__destroy(link);
+	if (pe_fd >= 0)
+		close(pe_fd);
+	if (pid > 0) {
+		write(pipefd[1], &buf, 1);
+		waitpid(pid, &status, 0);
+	}
+	if (pipefd[0] >= 0)
+		close(pipefd[0]);
+	if (pipefd[1] >= 0)
+		close(pipefd[1]);
+	return ret;
+}
+
+static int timer_stress_nmi_race(struct timer *timer_skel)
+{
+	int err;
+
+	err = run_nmi_test(timer_skel, timer_skel->progs.nmi_race);
+	if (err == EOPNOTSUPP)
+		return 0;
+	return err;
+}
+
+static int timer_stress_nmi_update(struct timer *timer_skel)
+{
+	int err;
+
+	err = run_nmi_test(timer_skel, timer_skel->progs.nmi_update);
+	if (err == EOPNOTSUPP)
+		return 0;
+	if (err)
+		return err;
+	ASSERT_GT(timer_skel->bss->update_hits, 0, "update_hits");
+	return 0;
+}
+
+static int timer_stress_nmi_cancel(struct timer *timer_skel)
+{
+	int err;
+
+	err = run_nmi_test(timer_skel, timer_skel->progs.nmi_cancel);
+	if (err == EOPNOTSUPP)
+		return 0;
+	if (err)
+		return err;
+	ASSERT_GT(timer_skel->bss->cancel_hits, 0, "cancel_hits");
+	return 0;
+}
+
+static int timer(struct timer *timer_skel)
+{
+	int err, prog_fd;
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+
 	err = timer__attach(timer_skel);
 	if (!ASSERT_OK(err, "timer_attach"))
 		return err;
@@ -63,25 +239,30 @@ static int timer(struct timer *timer_skel)
 	/* check that code paths completed */
 	ASSERT_EQ(timer_skel->bss->ok, 1 | 2 | 4, "ok");
 
-	prog_fd = bpf_program__fd(timer_skel->progs.race);
-	for (i = 0; i < NUM_THR; i++) {
-		err = pthread_create(&thread_id[i], NULL,
-				     &spin_lock_thread, &prog_fd);
-		if (!ASSERT_OK(err, "pthread_create"))
-			break;
-	}
+	return 0;
+}
 
-	while (i) {
-		err = pthread_join(thread_id[--i], &ret);
-		if (ASSERT_OK(err, "pthread_join"))
-			ASSERT_EQ(ret, (void *)&prog_fd, "pthread_join");
-	}
+static int timer_cancel_async(struct timer *timer_skel)
+{
+	int err, prog_fd;
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+	prog_fd = bpf_program__fd(timer_skel->progs.test_async_cancel_succeed);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(topts.retval, 0, "test_run");
+
+	usleep(500);
+	/* check that there were no errors in timer execution */
+	ASSERT_EQ(timer_skel->bss->err, 0, "err");
+
+	/* check that code paths completed */
+	ASSERT_EQ(timer_skel->bss->ok, 1 | 2 | 4, "ok");
 
 	return 0;
 }
 
-/* TODO: use pid filtering */
-void serial_test_timer(void)
+static void test_timer(int (*timer_test_fn)(struct timer *timer_skel))
 {
 	struct timer *timer_skel = NULL;
 	int err;
@@ -94,13 +275,48 @@ void serial_test_timer(void)
 	if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load"))
 		return;
 
-	err = timer(timer_skel);
+	err = timer_test_fn(timer_skel);
 	ASSERT_OK(err, "timer");
 	timer__destroy(timer_skel);
+}
+
+void serial_test_timer(void)
+{
+	test_timer(timer);
 
 	RUN_TESTS(timer_failure);
 }
 
+void serial_test_timer_stress(void)
+{
+	test_timer(timer_stress);
+}
+
+void serial_test_timer_stress_async_cancel(void)
+{
+	test_timer(timer_stress_async_cancel);
+}
+
+void serial_test_timer_async_cancel(void)
+{
+	test_timer(timer_cancel_async);
+}
+
+void serial_test_timer_stress_nmi_race(void)
+{
+	test_timer(timer_stress_nmi_race);
+}
+
+void serial_test_timer_stress_nmi_update(void)
+{
+	test_timer(timer_stress_nmi_update);
+}
+
+void serial_test_timer_stress_nmi_cancel(void)
+{
+	test_timer(timer_stress_nmi_cancel);
+}
+
 void test_timer_interrupt(void)
 {
 	struct timer_interrupt *skel = NULL;
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_start_deadlock.c b/tools/testing/selftests/bpf/prog_tests/timer_start_deadlock.c
new file mode 100644
index 000000000000..9f1f9aec8888
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/timer_start_deadlock.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include "timer_start_deadlock.skel.h"
+
+void test_timer_start_deadlock(void)
+{
+	struct timer_start_deadlock *skel;
+	int err, prog_fd;
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+
+	skel = timer_start_deadlock__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	err = timer_start_deadlock__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.start_timer);
+
+	/*
+	 * Run the syscall program that attempts to deadlock.
+	 * If the kernel deadlocks, this call will never return.
+	 */
+	err = bpf_prog_test_run_opts(prog_fd, &opts);
+	ASSERT_OK(err, "prog_test_run");
+	ASSERT_EQ(opts.retval, 0, "prog_retval");
+
+	ASSERT_EQ(skel->bss->tp_called, 1, "tp_called");
+cleanup:
+	timer_start_deadlock__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_start_delete_race.c b/tools/testing/selftests/bpf/prog_tests/timer_start_delete_race.c
new file mode 100644
index 000000000000..29a46e96f660
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/timer_start_delete_race.c
@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#define _GNU_SOURCE
+#include <sched.h>
+#include <pthread.h>
+#include <test_progs.h>
+#include "timer_start_delete_race.skel.h"
+
+/*
+ * Test for race between bpf_timer_start() and map element deletion.
+ *
+ * The race scenario:
+ * - CPU 1: bpf_timer_start() proceeds to bpf_async_process() and is about
+ *          to call hrtimer_start() but hasn't yet
+ * - CPU 2: map_delete_elem() calls __bpf_async_cancel_and_free(), since
+ *          timer is not scheduled yet hrtimer_try_to_cancel() is a nop,
+ *          then calls bpf_async_refcount_put() dropping refcnt to zero
+ *          and scheduling call_rcu_tasks_trace()
+ * - CPU 1: continues and calls hrtimer_start()
+ * - After RCU tasks trace grace period: memory is freed
+ * - Timer callback fires on freed memory: UAF!
+ *
+ * This test stresses this race by having two threads:
+ * - Thread 1: repeatedly starts timers
+ * - Thread 2: repeatedly deletes map elements
+ *
+ * KASAN should detect use-after-free.
+ */
+
+#define ITERATIONS 1000
+
+struct ctx {
+	struct timer_start_delete_race *skel;
+	volatile bool start;
+	volatile bool stop;
+	int errors;
+};
+
+static void *start_timer_thread(void *arg)
+{
+	struct ctx *ctx = arg;
+	cpu_set_t cpuset;
+	int fd, i;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+	pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset);
+
+	while (!ctx->start && !ctx->stop)
+		usleep(1);
+	if (ctx->stop)
+		return NULL;
+
+	fd = bpf_program__fd(ctx->skel->progs.start_timer);
+
+	for (i = 0; i < ITERATIONS && !ctx->stop; i++) {
+		LIBBPF_OPTS(bpf_test_run_opts, opts);
+		int err;
+
+		err = bpf_prog_test_run_opts(fd, &opts);
+		if (err || opts.retval) {
+			ctx->errors++;
+			break;
+		}
+	}
+
+	return NULL;
+}
+
+static void *delete_elem_thread(void *arg)
+{
+	struct ctx *ctx = arg;
+	cpu_set_t cpuset;
+	int fd, i;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(1, &cpuset);
+	pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset);
+
+	while (!ctx->start && !ctx->stop)
+		usleep(1);
+	if (ctx->stop)
+		return NULL;
+
+	fd = bpf_program__fd(ctx->skel->progs.delete_elem);
+
+	for (i = 0; i < ITERATIONS && !ctx->stop; i++) {
+		LIBBPF_OPTS(bpf_test_run_opts, opts);
+		int err;
+
+		err = bpf_prog_test_run_opts(fd, &opts);
+		if (err || opts.retval) {
+			ctx->errors++;
+			break;
+		}
+	}
+
+	return NULL;
+}
+
+void test_timer_start_delete_race(void)
+{
+	struct timer_start_delete_race *skel;
+	pthread_t threads[2];
+	struct ctx ctx = {};
+	int err;
+
+	skel = timer_start_delete_race__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	ctx.skel = skel;
+
+	err = pthread_create(&threads[0], NULL, start_timer_thread, &ctx);
+	if (!ASSERT_OK(err, "create start_timer_thread")) {
+		ctx.stop = true;
+		goto cleanup;
+	}
+
+	err = pthread_create(&threads[1], NULL, delete_elem_thread, &ctx);
+	if (!ASSERT_OK(err, "create delete_elem_thread")) {
+		ctx.stop = true;
+		pthread_join(threads[0], NULL);
+		goto cleanup;
+	}
+
+	ctx.start = true;
+
+	pthread_join(threads[0], NULL);
+	pthread_join(threads[1], NULL);
+
+	ASSERT_EQ(ctx.errors, 0, "thread_errors");
+
+	/* Either KASAN will catch UAF or kernel will crash or nothing happens */
+cleanup:
+	timer_start_delete_race__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tracing_failure.c b/tools/testing/selftests/bpf/prog_tests/tracing_failure.c
index 10e231965589..f9f9e1cb87bf 100644
--- a/tools/testing/selftests/bpf/prog_tests/tracing_failure.c
+++ b/tools/testing/selftests/bpf/prog_tests/tracing_failure.c
@@ -73,7 +73,7 @@ static void test_tracing_deny(void)
 static void test_fexit_noreturns(void)
 {
 	test_tracing_fail_prog("fexit_noreturns",
-			       "Attaching fexit/fmod_ret to __noreturn function 'do_exit' is rejected.");
+			       "Attaching fexit/fsession/fmod_ret to __noreturn function 'do_exit' is rejected.");
 }
 
 void test_tracing_failure(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index 4b4b081b46cc..302286a80154 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -6,6 +6,8 @@
 #include "verifier_and.skel.h"
 #include "verifier_arena.skel.h"
 #include "verifier_arena_large.skel.h"
+#include "verifier_arena_globals1.skel.h"
+#include "verifier_arena_globals2.skel.h"
 #include "verifier_array_access.skel.h"
 #include "verifier_async_cb_context.skel.h"
 #include "verifier_basic_stack.skel.h"
@@ -28,9 +30,11 @@
 #include "verifier_ctx.skel.h"
 #include "verifier_ctx_sk_msg.skel.h"
 #include "verifier_d_path.skel.h"
+#include "verifier_default_trusted_ptr.skel.h"
 #include "verifier_direct_packet_access.skel.h"
 #include "verifier_direct_stack_access_wraparound.skel.h"
 #include "verifier_div0.skel.h"
+#include "verifier_div_mod_bounds.skel.h"
 #include "verifier_div_overflow.skel.h"
 #include "verifier_global_subprogs.skel.h"
 #include "verifier_global_ptr_args.skel.h"
@@ -108,6 +112,7 @@
 #include "verifier_xdp_direct_packet_access.skel.h"
 #include "verifier_bits_iter.skel.h"
 #include "verifier_lsm.skel.h"
+#include "verifier_jit_inline.skel.h"
 #include "irq.skel.h"
 
 #define MAX_ENTRIES 11
@@ -147,6 +152,8 @@ static void run_tests_aux(const char *skel_name,
 void test_verifier_and(void)                  { RUN(verifier_and); }
 void test_verifier_arena(void)                { RUN(verifier_arena); }
 void test_verifier_arena_large(void)          { RUN(verifier_arena_large); }
+void test_verifier_arena_globals1(void)       { RUN(verifier_arena_globals1); }
+void test_verifier_arena_globals2(void)       { RUN(verifier_arena_globals2); }
 void test_verifier_basic_stack(void)          { RUN(verifier_basic_stack); }
 void test_verifier_bitfield_write(void)       { RUN(verifier_bitfield_write); }
 void test_verifier_bounds(void)               { RUN(verifier_bounds); }
@@ -167,9 +174,11 @@ 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); }
 void test_verifier_d_path(void)               { RUN(verifier_d_path); }
+void test_verifier_default_trusted_ptr(void)  { RUN_TESTS(verifier_default_trusted_ptr); }
 void test_verifier_direct_packet_access(void) { RUN(verifier_direct_packet_access); }
 void test_verifier_direct_stack_access_wraparound(void) { RUN(verifier_direct_stack_access_wraparound); }
 void test_verifier_div0(void)                 { RUN(verifier_div0); }
+void test_verifier_div_mod_bounds(void)       { RUN(verifier_div_mod_bounds); }
 void test_verifier_div_overflow(void)         { RUN(verifier_div_overflow); }
 void test_verifier_global_subprogs(void)      { RUN(verifier_global_subprogs); }
 void test_verifier_global_ptr_args(void)      { RUN(verifier_global_ptr_args); }
@@ -247,6 +256,7 @@ void test_verifier_bits_iter(void) { RUN(verifier_bits_iter); }
 void test_verifier_lsm(void)                  { RUN(verifier_lsm); }
 void test_irq(void)			      { RUN(irq); }
 void test_verifier_mtu(void)		      { RUN(verifier_mtu); }
+void test_verifier_jit_inline(void)               { RUN(verifier_jit_inline); }
 
 static int init_test_val_map(struct bpf_object *obj, char *map_name)
 {
diff --git a/tools/testing/selftests/bpf/prog_tests/wq.c b/tools/testing/selftests/bpf/prog_tests/wq.c
index 15c67d23128b..84831eecc935 100644
--- a/tools/testing/selftests/bpf/prog_tests/wq.c
+++ b/tools/testing/selftests/bpf/prog_tests/wq.c
@@ -16,12 +16,12 @@ void serial_test_wq(void)
 	/* re-run the success test to check if the timer was actually executed */
 
 	wq_skel = wq__open_and_load();
-	if (!ASSERT_OK_PTR(wq_skel, "wq_skel_load"))
+	if (!ASSERT_OK_PTR(wq_skel, "wq__open_and_load"))
 		return;
 
 	err = wq__attach(wq_skel);
 	if (!ASSERT_OK(err, "wq_attach"))
-		return;
+		goto clean_up;
 
 	prog_fd = bpf_program__fd(wq_skel->progs.test_syscall_array_sleepable);
 	err = bpf_prog_test_run_opts(prog_fd, &topts);
@@ -31,6 +31,7 @@ void serial_test_wq(void)
 	usleep(50); /* 10 usecs should be enough, but give it extra */
 
 	ASSERT_EQ(wq_skel->bss->ok_sleepable, (1 << 1), "ok_sleepable");
+clean_up:
 	wq__destroy(wq_skel);
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
index df27535995af..ad56e4370ce3 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
@@ -18,7 +18,7 @@ static void test_xdp_with_cpumap_helpers(void)
 	struct bpf_cpumap_val val = {
 		.qsize = 192,
 	};
-	int err, prog_fd, prog_redir_fd, map_fd;
+	int err, prog_fd, prog_redir_fd, map_fd, bad_fd;
 	struct nstoken *nstoken = NULL;
 	__u32 idx = 0;
 
@@ -79,7 +79,22 @@ static void test_xdp_with_cpumap_helpers(void)
 	val.qsize = 192;
 	val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_prog);
 	err = bpf_map_update_elem(map_fd, &idx, &val, 0);
-	ASSERT_NEQ(err, 0, "Add non-BPF_XDP_CPUMAP program to cpumap entry");
+	ASSERT_EQ(err, -EINVAL, "Add non-BPF_XDP_CPUMAP program to cpumap entry");
+
+	/* Try to attach non-BPF file descriptor */
+	bad_fd = open("/dev/null", O_RDONLY);
+	ASSERT_GE(bad_fd, 0, "Open /dev/null for non-BPF fd");
+
+	val.bpf_prog.fd = bad_fd;
+	err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+	ASSERT_EQ(err, -EINVAL, "Add non-BPF fd to cpumap entry");
+
+	/* Try to attach nonexistent file descriptor */
+	err = close(bad_fd);
+	ASSERT_EQ(err, 0, "Close non-BPF fd for nonexistent fd");
+
+	err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+	ASSERT_EQ(err, -EBADF, "Add nonexistent fd to cpumap entry");
 
 	/* Try to attach BPF_XDP program with frags to cpumap when we have
 	 * already loaded a BPF_XDP program on the map
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c b/tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c
index efa350d04ec5..910dabe95afd 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c
@@ -114,12 +114,14 @@ static void test_xdp_pull_data_basic(void)
 {
 	u32 pg_sz, max_meta_len, max_data_len;
 	struct test_xdp_pull_data *skel;
+	int buff_len;
 
 	skel = test_xdp_pull_data__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "test_xdp_pull_data__open_and_load"))
 		return;
 
 	pg_sz = sysconf(_SC_PAGE_SIZE);
+	buff_len = pg_sz + pg_sz / 2;
 
 	if (find_xdp_sizes(skel, pg_sz))
 		goto out;
@@ -140,13 +142,13 @@ static void test_xdp_pull_data_basic(void)
 	run_test(skel, XDP_PASS, pg_sz, 9000, 0, 1025, 1025);
 
 	/* multi-buf pkt, empty linear data area, pull requires memmove */
-	run_test(skel, XDP_PASS, pg_sz, 9000, 0, 0, PULL_MAX);
+	run_test(skel, XDP_PASS, pg_sz, buff_len, 0, 0, PULL_MAX);
 
 	/* multi-buf pkt, no headroom */
-	run_test(skel, XDP_PASS, pg_sz, 9000, max_meta_len, 1024, PULL_MAX);
+	run_test(skel, XDP_PASS, pg_sz, buff_len, max_meta_len, 1024, PULL_MAX);
 
 	/* multi-buf pkt, no tailroom, pull requires memmove */
-	run_test(skel, XDP_PASS, pg_sz, 9000, 0, max_data_len, PULL_MAX);
+	run_test(skel, XDP_PASS, pg_sz, buff_len, 0, max_data_len, PULL_MAX);
 
 	/* Test cases with invalid pull length */
 
@@ -154,18 +156,18 @@ static void test_xdp_pull_data_basic(void)
 	run_test(skel, XDP_DROP, pg_sz, 2048, 0, 2048, 2049);
 
 	/* multi-buf pkt with no space left in linear data area */
-	run_test(skel, XDP_DROP, pg_sz, 9000, max_meta_len, max_data_len,
+	run_test(skel, XDP_DROP, pg_sz, buff_len, max_meta_len, max_data_len,
 		 PULL_MAX | PULL_PLUS_ONE);
 
 	/* multi-buf pkt, empty linear data area */
-	run_test(skel, XDP_DROP, pg_sz, 9000, 0, 0, PULL_MAX | PULL_PLUS_ONE);
+	run_test(skel, XDP_DROP, pg_sz, buff_len, 0, 0, PULL_MAX | PULL_PLUS_ONE);
 
 	/* multi-buf pkt, no headroom */
-	run_test(skel, XDP_DROP, pg_sz, 9000, max_meta_len, 1024,
+	run_test(skel, XDP_DROP, pg_sz, buff_len, max_meta_len, 1024,
 		 PULL_MAX | PULL_PLUS_ONE);
 
 	/* multi-buf pkt, no tailroom */
-	run_test(skel, XDP_DROP, pg_sz, 9000, 0, max_data_len,
+	run_test(skel, XDP_DROP, pg_sz, buff_len, 0, max_data_len,
 		 PULL_MAX | PULL_PLUS_ONE);
 
 out:
diff --git a/tools/testing/selftests/bpf/progs/arena_list.c b/tools/testing/selftests/bpf/progs/arena_list.c
index 3a2ddcacbea6..235d8cc95bdd 100644
--- a/tools/testing/selftests/bpf/progs/arena_list.c
+++ b/tools/testing/selftests/bpf/progs/arena_list.c
@@ -30,6 +30,7 @@ struct arena_list_head __arena *list_head;
 int list_sum;
 int cnt;
 bool skip = false;
+const volatile bool nonsleepable = false;
 
 #ifdef __BPF_FEATURE_ADDR_SPACE_CAST
 long __arena arena_sum;
@@ -42,6 +43,9 @@ int test_val SEC(".addr_space.1");
 
 int zero;
 
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+
 SEC("syscall")
 int arena_list_add(void *ctx)
 {
@@ -71,6 +75,10 @@ int arena_list_del(void *ctx)
 	struct elem __arena *n;
 	int sum = 0;
 
+	/* Take rcu_read_lock to test non-sleepable context */
+	if (nonsleepable)
+		bpf_rcu_read_lock();
+
 	arena_sum = 0;
 	list_for_each_entry(n, list_head, node) {
 		sum += n->value;
@@ -79,6 +87,9 @@ int arena_list_del(void *ctx)
 		bpf_free(n);
 	}
 	list_sum = sum;
+
+	if (nonsleepable)
+		bpf_rcu_read_unlock();
 #else
 	skip = true;
 #endif
diff --git a/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c b/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c
index ff189a736ad8..8fc38592a87b 100644
--- a/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c
+++ b/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c
@@ -62,9 +62,9 @@ static int create_attach_counter(__u64 cg_id, __u64 state, __u64 pending)
 				   &init, BPF_NOEXIST);
 }
 
-SEC("fentry/cgroup_attach_task")
-int BPF_PROG(counter, struct cgroup *dst_cgrp, struct task_struct *leader,
-	     bool threadgroup)
+SEC("tp_btf/cgroup_attach_task")
+int BPF_PROG(counter, struct cgroup *dst_cgrp, const char *path,
+	     struct task_struct *task, bool threadgroup)
 {
 	__u64 cg_id = cgroup_id(dst_cgrp);
 	struct percpu_attach_counter *pcpu_counter = bpf_map_lookup_elem(
diff --git a/tools/testing/selftests/bpf/progs/cgroup_iter_memcg.c b/tools/testing/selftests/bpf/progs/cgroup_iter_memcg.c
new file mode 100644
index 000000000000..59fb70a3cc50
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cgroup_iter_memcg.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_core_read.h>
+#include "cgroup_iter_memcg.h"
+
+char _license[] SEC("license") = "GPL";
+
+/* The latest values read are stored here. */
+struct memcg_query memcg_query SEC(".data.query");
+
+SEC("iter.s/cgroup")
+int cgroup_memcg_query(struct bpf_iter__cgroup *ctx)
+{
+	struct cgroup *cgrp = ctx->cgroup;
+	struct cgroup_subsys_state *css;
+	struct mem_cgroup *memcg;
+
+	if (!cgrp)
+		return 1;
+
+	css = &cgrp->self;
+	memcg = bpf_get_mem_cgroup(css);
+	if (!memcg)
+		return 1;
+
+	bpf_mem_cgroup_flush_stats(memcg);
+
+	memcg_query.nr_anon_mapped = bpf_mem_cgroup_page_state(memcg, NR_ANON_MAPPED);
+	memcg_query.nr_shmem = bpf_mem_cgroup_page_state(memcg, NR_SHMEM);
+	memcg_query.nr_file_pages = bpf_mem_cgroup_page_state(memcg, NR_FILE_PAGES);
+	memcg_query.nr_file_mapped = bpf_mem_cgroup_page_state(memcg, NR_FILE_MAPPED);
+	memcg_query.memcg_kmem = bpf_mem_cgroup_page_state(memcg, MEMCG_KMEM);
+	memcg_query.pgfault = bpf_mem_cgroup_vm_events(memcg, PGFAULT);
+
+	bpf_put_mem_cgroup(memcg);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/compute_live_registers.c b/tools/testing/selftests/bpf/progs/compute_live_registers.c
index 6884ab99a421..f05e120f3450 100644
--- a/tools/testing/selftests/bpf/progs/compute_live_registers.c
+++ b/tools/testing/selftests/bpf/progs/compute_live_registers.c
@@ -431,6 +431,47 @@ __naked void subprog1(void)
 		::: __clobber_all);
 }
 
+#if defined(__TARGET_ARCH_x86) || defined(__TARGET_ARCH_arm64)
+
+SEC("socket")
+__log_level(2)
+__msg("2: .1........ (07) r1 += 8")
+__msg("3: .1........ (79) r2 = *(u64 *)(r1 +0)")
+__msg("4: ..2....... (b7) r3 = 1")
+__msg("5: ..23...... (b7) r4 = 2")
+__msg("6: ..234..... (0d) gotox r2")
+__msg("7: ...3...... (bf) r0 = r3")
+__msg("8: 0......... (95) exit")
+__msg("9: ....4..... (bf) r0 = r4")
+__msg("10: 0......... (95) exit")
+__naked
+void gotox(void)
+{
+	asm volatile (
+	".pushsection .jumptables,\"\",@progbits;"
+"jt0_%=: .quad l0_%= - socket;"
+	".quad l1_%= - socket;"
+	".size jt0_%=, 16;"
+	".global jt0_%=;"
+	".popsection;"
+
+	"r1 = jt0_%= ll;"
+	"r1 += 8;"
+	"r2 = *(u64 *)(r1 + 0);"
+	"r3 = 1;"
+	"r4 = 2;"
+	".8byte %[gotox_r2];"
+"l0_%=:  r0 = r3;"
+	"exit;"
+"l1_%=:  r0 = r4;"
+	"exit;"
+	:
+	: __imm_insn(gotox_r2, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_2, BPF_REG_0, 0, 0))
+	: __clobber_all);
+}
+
+#endif /* __TARGET_ARCH_x86 || __TARGET_ARCH_arm64 */
+
 /* to retain debug info for BTF generation */
 void kfunc_root(void)
 {
diff --git a/tools/testing/selftests/bpf/progs/cpumask_failure.c b/tools/testing/selftests/bpf/progs/cpumask_failure.c
index 8a2fd596c8a3..61c32e91e8c3 100644
--- a/tools/testing/selftests/bpf/progs/cpumask_failure.c
+++ b/tools/testing/selftests/bpf/progs/cpumask_failure.c
@@ -110,7 +110,7 @@ SEC("tp_btf/task_newtask")
 __failure __msg("NULL pointer passed to trusted arg0")
 int BPF_PROG(test_cpumask_null, struct task_struct *task, u64 clone_flags)
 {
-  /* NULL passed to KF_TRUSTED_ARGS kfunc. */
+  /* NULL passed to kfunc. */
 	bpf_cpumask_empty(NULL);
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c
index dda6a8dada82..8f2ae9640886 100644
--- a/tools/testing/selftests/bpf/progs/dynptr_fail.c
+++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c
@@ -1465,7 +1465,7 @@ int xdp_invalid_data_slice2(struct xdp_md *xdp)
 }
 
 /* Only supported prog type can create skb-type dynptrs */
-SEC("?raw_tp")
+SEC("?xdp")
 __failure __msg("calling kernel function bpf_dynptr_from_skb is not allowed")
 int skb_invalid_ctx(void *ctx)
 {
diff --git a/tools/testing/selftests/bpf/progs/file_reader.c b/tools/testing/selftests/bpf/progs/file_reader.c
index 4d756b623557..462712ff3b8a 100644
--- a/tools/testing/selftests/bpf/progs/file_reader.c
+++ b/tools/testing/selftests/bpf/progs/file_reader.c
@@ -77,7 +77,7 @@ int on_open_validate_file_read(void *c)
 		err = 1;
 		return 0;
 	}
-	bpf_task_work_schedule_signal_impl(task, &work->tw, &arrmap, task_work_callback, NULL);
+	bpf_task_work_schedule_signal(task, &work->tw, &arrmap, task_work_callback);
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/free_timer.c b/tools/testing/selftests/bpf/progs/free_timer.c
index 4501ae8fc414..eccb2d47db43 100644
--- a/tools/testing/selftests/bpf/progs/free_timer.c
+++ b/tools/testing/selftests/bpf/progs/free_timer.c
@@ -7,6 +7,16 @@
 
 #define MAX_ENTRIES 8
 
+/* clang considers 'sum += 1' as usage but 'sum++' as non-usage.  GCC
+ * is more consistent and considers both 'sum += 1' and 'sum++' as
+ * non-usage.  This triggers warnings in the functions below.
+ *
+ * Starting with GCC 16 -Wunused-but-set-variable=2 can be used to
+ * mimic clang's behavior.  */
+#if !defined(__clang__) && __GNUC__ > 15
+#pragma GCC diagnostic ignored "-Wunused-but-set-variable"
+#endif
+
 struct map_value {
 	struct bpf_timer timer;
 };
diff --git a/tools/testing/selftests/bpf/progs/fsession_test.c b/tools/testing/selftests/bpf/progs/fsession_test.c
new file mode 100644
index 000000000000..86e8a2fe467e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fsession_test.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 ChinaTelecom */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 test1_entry_result = 0;
+__u64 test1_exit_result = 0;
+
+SEC("fsession/bpf_fentry_test1")
+int BPF_PROG(test1, int a, int ret)
+{
+	bool is_exit = bpf_session_is_return(ctx);
+
+	if (!is_exit) {
+		test1_entry_result = a == 1 && ret == 0;
+		return 0;
+	}
+
+	test1_exit_result = a == 1 && ret == 2;
+	return 0;
+}
+
+__u64 test2_entry_result = 0;
+__u64 test2_exit_result = 0;
+
+SEC("fsession/bpf_fentry_test3")
+int BPF_PROG(test2, char a, int b, __u64 c, int ret)
+{
+	bool is_exit = bpf_session_is_return(ctx);
+
+	if (!is_exit) {
+		test2_entry_result = a == 4 && b == 5 && c == 6 && ret == 0;
+		return 0;
+	}
+
+	test2_exit_result = a == 4 && b == 5 && c == 6 && ret == 15;
+	return 0;
+}
+
+__u64 test3_entry_result = 0;
+__u64 test3_exit_result = 0;
+
+SEC("fsession/bpf_fentry_test4")
+int BPF_PROG(test3, void *a, char b, int c, __u64 d, int ret)
+{
+	bool is_exit = bpf_session_is_return(ctx);
+
+	if (!is_exit) {
+		test3_entry_result = a == (void *)7 && b == 8 && c == 9 && d == 10 && ret == 0;
+		return 0;
+	}
+
+	test3_exit_result = a == (void *)7 && b == 8 && c == 9 && d == 10 && ret == 34;
+	return 0;
+}
+
+__u64 test4_entry_result = 0;
+__u64 test4_exit_result = 0;
+
+SEC("fsession/bpf_fentry_test5")
+int BPF_PROG(test4, __u64 a, void *b, short c, int d, __u64 e, int ret)
+{
+	bool is_exit = bpf_session_is_return(ctx);
+
+	if (!is_exit) {
+		test4_entry_result = a == 11 && b == (void *)12 && c == 13 && d == 14 &&
+			e == 15 && ret == 0;
+		return 0;
+	}
+
+	test4_exit_result = a == 11 && b == (void *)12 && c == 13 && d == 14 &&
+		e == 15 && ret == 65;
+	return 0;
+}
+
+__u64 test5_entry_result = 0;
+__u64 test5_exit_result = 0;
+
+SEC("fsession/bpf_fentry_test7")
+int BPF_PROG(test5, struct bpf_fentry_test_t *arg, int ret)
+{
+	bool is_exit = bpf_session_is_return(ctx);
+
+	if (!is_exit) {
+		if (!arg)
+			test5_entry_result = ret == 0;
+		return 0;
+	}
+
+	if (!arg)
+		test5_exit_result = 1;
+	return 0;
+}
+
+__u64 test6_entry_result = 0;
+__u64 test6_exit_result = 0;
+SEC("fsession/bpf_fentry_test1")
+int BPF_PROG(test6, int a)
+{
+	__u64 addr = bpf_get_func_ip(ctx);
+
+	if (bpf_session_is_return(ctx))
+		test6_exit_result = (const void *) addr == &bpf_fentry_test1;
+	else
+		test6_entry_result = (const void *) addr == &bpf_fentry_test1;
+	return 0;
+}
+
+__u64 test7_entry_ok = 0;
+__u64 test7_exit_ok = 0;
+SEC("fsession/bpf_fentry_test1")
+int BPF_PROG(test7, int a)
+{
+	volatile __u64 *cookie = bpf_session_cookie(ctx);
+
+	if (!bpf_session_is_return(ctx)) {
+		*cookie = 0xAAAABBBBCCCCDDDDull;
+		test7_entry_ok = *cookie == 0xAAAABBBBCCCCDDDDull;
+		return 0;
+	}
+
+	test7_exit_ok = *cookie == 0xAAAABBBBCCCCDDDDull;
+	return 0;
+}
+
+__u64 test8_entry_ok = 0;
+__u64 test8_exit_ok = 0;
+
+SEC("fsession/bpf_fentry_test1")
+int BPF_PROG(test8, int a)
+{
+	volatile __u64 *cookie = bpf_session_cookie(ctx);
+
+	if (!bpf_session_is_return(ctx)) {
+		*cookie = 0x1111222233334444ull;
+		test8_entry_ok = *cookie == 0x1111222233334444ull;
+		return 0;
+	}
+
+	test8_exit_ok = *cookie == 0x1111222233334444ull;
+	return 0;
+}
+
+__u64 test9_entry_result = 0;
+__u64 test9_exit_result = 0;
+
+SEC("fsession/bpf_fentry_test1")
+int BPF_PROG(test9, int a, int ret)
+{
+	__u64 *cookie = bpf_session_cookie(ctx);
+
+	if (!bpf_session_is_return(ctx)) {
+		test9_entry_result = a == 1 && ret == 0;
+		*cookie = 0x123456ULL;
+		return 0;
+	}
+
+	test9_exit_result = a == 1 && ret == 2 && *cookie == 0x123456ULL;
+	return 0;
+}
+
+__u64 test10_result = 0;
+SEC("fexit/bpf_fentry_test1")
+int BPF_PROG(test10, int a, int ret)
+{
+	test10_result = a == 1 && ret == 2;
+	return 0;
+}
+
+__u64 test11_result = 0;
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(test11, int a)
+{
+	test11_result = a == 1;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/get_func_args_test.c b/tools/testing/selftests/bpf/progs/get_func_args_test.c
index e0f34a55e697..180ba5098ca1 100644
--- a/tools/testing/selftests/bpf/progs/get_func_args_test.c
+++ b/tools/testing/selftests/bpf/progs/get_func_args_test.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/bpf.h>
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include <errno.h>
@@ -121,3 +121,85 @@ int BPF_PROG(fexit_test, int _a, int *_b, int _ret)
 	test4_result &= err == 0 && ret == 1234;
 	return 0;
 }
+
+__u64 test5_result = 0;
+SEC("tp_btf/bpf_testmod_fentry_test1_tp")
+int BPF_PROG(tp_test1)
+{
+	__u64 cnt = bpf_get_func_arg_cnt(ctx);
+	__u64 a = 0, z = 0;
+	__s64 err;
+
+	test5_result = cnt == 1;
+
+	err = bpf_get_func_arg(ctx, 0, &a);
+	test5_result &= err == 0 && ((int) a == 1);
+
+	/* not valid argument */
+	err = bpf_get_func_arg(ctx, 1, &z);
+	test5_result &= err == -EINVAL;
+
+	return 0;
+}
+
+__u64 test6_result = 0;
+SEC("tp_btf/bpf_testmod_fentry_test2_tp")
+int BPF_PROG(tp_test2)
+{
+	__u64 cnt = bpf_get_func_arg_cnt(ctx);
+	__u64 a = 0, b = 0, z = 0;
+	__s64 err;
+
+	test6_result = cnt == 2;
+
+	/* valid arguments */
+	err = bpf_get_func_arg(ctx, 0, &a);
+	test6_result &= err == 0 && (int) a == 2;
+
+	err = bpf_get_func_arg(ctx, 1, &b);
+	test6_result &= err == 0 && b == 3;
+
+	/* not valid argument */
+	err = bpf_get_func_arg(ctx, 2, &z);
+	test6_result &= err == -EINVAL;
+
+	return 0;
+}
+
+__u64 test7_result = 0;
+#if defined(bpf_target_x86) || defined(bpf_target_arm64)
+SEC("fsession/bpf_fentry_test1")
+int BPF_PROG(test7)
+{
+	__u64 cnt = bpf_get_func_arg_cnt(ctx);
+	__u64 a = 0, z = 0, ret = 0;
+	__s64 err;
+
+	test7_result = cnt == 1;
+
+	/* valid arguments */
+	err = bpf_get_func_arg(ctx, 0, &a);
+	test7_result &= err == 0 && ((int) a == 1);
+
+	/* not valid argument */
+	err = bpf_get_func_arg(ctx, 1, &z);
+	test7_result &= err == -EINVAL;
+
+	if (bpf_session_is_return(ctx)) {
+		err = bpf_get_func_ret(ctx, &ret);
+		test7_result &= err == 0 && ret == 2;
+	} else {
+		err = bpf_get_func_ret(ctx, &ret);
+		test7_result &= err == 0 && ret == 0;
+	}
+
+	return 0;
+}
+#else
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(test7)
+{
+	test7_result = 1;
+	return 0;
+}
+#endif
diff --git a/tools/testing/selftests/bpf/progs/get_func_ip_test.c b/tools/testing/selftests/bpf/progs/get_func_ip_test.c
index 2011cacdeb18..43ff836a8ed8 100644
--- a/tools/testing/selftests/bpf/progs/get_func_ip_test.c
+++ b/tools/testing/selftests/bpf/progs/get_func_ip_test.c
@@ -103,3 +103,26 @@ int BPF_URETPROBE(test8, int ret)
 	test8_result = (const void *) addr == (const void *) uprobe_trigger;
 	return 0;
 }
+
+__u64 test9_entry_result = 0;
+__u64 test9_exit_result = 0;
+#if defined(bpf_target_x86) || defined(bpf_target_arm64)
+SEC("fsession/bpf_fentry_test1")
+int BPF_PROG(test9, int a)
+{
+	__u64 addr = bpf_get_func_ip(ctx);
+
+	if (bpf_session_is_return(ctx))
+		test9_exit_result = (const void *) addr == &bpf_fentry_test1;
+	else
+		test9_entry_result = (const void *) addr == &bpf_fentry_test1;
+	return 0;
+}
+#else
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(test9, int a)
+{
+	test9_entry_result = test9_exit_result = 1;
+	return 0;
+}
+#endif
diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
index 7dd92a303bf6..7f27b517d5d5 100644
--- a/tools/testing/selftests/bpf/progs/iters.c
+++ b/tools/testing/selftests/bpf/progs/iters.c
@@ -1926,4 +1926,144 @@ static int loop1_wrapper(void)
 	);
 }
 
+/*
+ * This is similar to a test case absent_mark_in_the_middle_state(),
+ * but adapted for use with bpf_loop().
+ */
+SEC("raw_tp")
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure __msg("math between fp pointer and register with unbounded min value is not allowed")
+__naked void absent_mark_in_the_middle_state4(void)
+{
+	/*
+	 * Equivalent to a C program below:
+	 *
+	 * int main(void) {
+	 *   fp[-8] = bpf_get_prandom_u32();
+	 *   fp[-16] = -32;                    // used in a memory access below
+	 *   bpf_loop(7, loop_cb4, fp, 0);
+	 *   return 0;
+	 * }
+	 *
+	 * int loop_cb4(int i, void *ctx) {
+	 *   if (unlikely(ctx[-8] > bpf_get_prandom_u32()))
+	 *     *(u64 *)(fp + ctx[-16]) = 42;   // aligned access expected
+	 *   if (unlikely(fp[-8] > bpf_get_prandom_u32()))
+	 *     ctx[-16] = -31;                 // makes said access unaligned
+	 *   return 0;
+	 * }
+	 */
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"r8 = r0;"
+		"*(u64 *)(r10 - 8) = r0;"
+		"*(u64 *)(r10 - 16) = -32;"
+		"r1 = 7;"
+		"r2 = loop_cb4 ll;"
+		"r3 = r10;"
+		"r4 = 0;"
+		"call %[bpf_loop];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_loop),
+		  __imm(bpf_get_prandom_u32)
+		: __clobber_all
+	);
+}
+
+__used __naked
+static void loop_cb4(void)
+{
+	asm volatile (
+		"r9 = r2;"
+		"r8 = *(u64 *)(r9 - 8);"
+		"r6 = *(u64 *)(r9 - 16);"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 > r8 goto use_fp16_%=;"
+	"1:"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 > r8 goto update_fp16_%=;"
+	"2:"
+		"r0 = 0;"
+		"exit;"
+	"use_fp16_%=:"
+		"r1 = r10;"
+		"r1 += r6;"
+		"*(u64 *)(r1 + 0) = 42;"
+		"goto 1b;"
+	"update_fp16_%=:"
+		"*(u64 *)(r9 - 16) = -31;"
+		"goto 2b;"
+		:
+		: __imm(bpf_get_prandom_u32)
+	);
+}
+
+SEC("raw_tp")
+__success
+__naked int stack_misc_vs_scalar_in_a_loop(void)
+{
+	asm volatile(
+		"*(u8 *)(r10 - 15) = 1;" /* This marks stack slot fp[-16] as STACK_MISC. */
+		"*(u8 *)(r10 - 23) = 1;"
+		"*(u8 *)(r10 - 31) = 1;"
+		"*(u8 *)(r10 - 39) = 1;"
+		"*(u8 *)(r10 - 47) = 1;"
+		"*(u8 *)(r10 - 55) = 1;"
+		"*(u8 *)(r10 - 63) = 1;"
+		"*(u8 *)(r10 - 71) = 1;"
+		"*(u8 *)(r10 - 79) = 1;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+	"loop_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto loop_end_%=;"
+
+#define maybe_change_stack_slot(off) \
+		"call %[bpf_get_prandom_u32];"	\
+		"if r0 == 42 goto +1;"		\
+		"goto +1;"			\
+		"*(u64 *)(r10 " #off ") = r0;"
+
+		/*
+		 * When comparing verifier states fp[-16] will be
+		 * either STACK_MISC or SCALAR. Pruning logic should
+		 * consider old STACK_MISC equivalent to current SCALAR
+		 * to avoid states explosion.
+		 */
+		maybe_change_stack_slot(-16)
+		maybe_change_stack_slot(-24)
+		maybe_change_stack_slot(-32)
+		maybe_change_stack_slot(-40)
+		maybe_change_stack_slot(-48)
+		maybe_change_stack_slot(-56)
+		maybe_change_stack_slot(-64)
+		maybe_change_stack_slot(-72)
+		maybe_change_stack_slot(-80)
+
+#undef maybe_change_stack_slot
+
+		"goto loop_%=;"
+	"loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy),
+		  __imm_addr(amap)
+		: __clobber_all
+	);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/iters_css.c b/tools/testing/selftests/bpf/progs/iters_css.c
index ec1f6c2f590b..5a1d87d186a9 100644
--- a/tools/testing/selftests/bpf/progs/iters_css.c
+++ b/tools/testing/selftests/bpf/progs/iters_css.c
@@ -12,8 +12,7 @@ char _license[] SEC("license") = "GPL";
 pid_t target_pid;
 u64 root_cg_id, leaf_cg_id;
 u64 first_cg_id, last_cg_id;
-
-int pre_order_cnt, post_order_cnt, tree_high;
+int pre_order_cnt, post_order_cnt, children_cnt, tree_high;
 
 struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
 void bpf_cgroup_release(struct cgroup *p) __ksym;
@@ -43,7 +42,7 @@ int iter_css_for_each(const void *ctx)
 	}
 	root_css = &root_cgrp->self;
 	leaf_css = &leaf_cgrp->self;
-	pre_order_cnt = post_order_cnt = tree_high = 0;
+	pre_order_cnt = post_order_cnt = children_cnt = tree_high = 0;
 	first_cg_id = last_cg_id = 0;
 
 	bpf_rcu_read_lock();
@@ -60,6 +59,10 @@ int iter_css_for_each(const void *ctx)
 			first_cg_id = cur_cgrp->kn->id;
 	}
 
+	bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_CHILDREN) {
+		children_cnt++;
+	}
+
 	bpf_for_each(css, pos, leaf_css, BPF_CGROUP_ITER_ANCESTORS_UP)
 		tree_high++;
 
diff --git a/tools/testing/selftests/bpf/progs/kfunc_implicit_args.c b/tools/testing/selftests/bpf/progs/kfunc_implicit_args.c
new file mode 100644
index 000000000000..89b6a47e22dd
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kfunc_implicit_args.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+extern int bpf_kfunc_implicit_arg(int a) __weak __ksym;
+extern int bpf_kfunc_implicit_arg_impl(int a, struct bpf_prog_aux *aux) __weak __ksym; /* illegal */
+extern int bpf_kfunc_implicit_arg_legacy(int a, int b) __weak __ksym;
+extern int bpf_kfunc_implicit_arg_legacy_impl(int a, int b, struct bpf_prog_aux *aux) __weak __ksym;
+
+char _license[] SEC("license") = "GPL";
+
+SEC("syscall")
+__retval(5)
+int test_kfunc_implicit_arg(void *ctx)
+{
+	return bpf_kfunc_implicit_arg(5);
+}
+
+SEC("syscall")
+__failure __msg("cannot find address for kernel function bpf_kfunc_implicit_arg_impl")
+int test_kfunc_implicit_arg_impl_illegal(void *ctx)
+{
+	return bpf_kfunc_implicit_arg_impl(5, NULL);
+}
+
+SEC("syscall")
+__retval(7)
+int test_kfunc_implicit_arg_legacy(void *ctx)
+{
+	return bpf_kfunc_implicit_arg_legacy(3, 4);
+}
+
+SEC("syscall")
+__retval(11)
+int test_kfunc_implicit_arg_legacy_impl(void *ctx)
+{
+	return bpf_kfunc_implicit_arg_legacy_impl(5, 6, NULL);
+}
diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi_override.c b/tools/testing/selftests/bpf/progs/kprobe_multi_override.c
index 28f8487c9059..14f39fa6d515 100644
--- a/tools/testing/selftests/bpf/progs/kprobe_multi_override.c
+++ b/tools/testing/selftests/bpf/progs/kprobe_multi_override.c
@@ -5,9 +5,24 @@
 
 char _license[] SEC("license") = "GPL";
 
+int pid = 0;
+
 SEC("kprobe.multi")
 int test_override(struct pt_regs *ctx)
 {
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	bpf_override_return(ctx, 123);
+	return 0;
+}
+
+SEC("kprobe")
+int test_kprobe_override(struct pt_regs *ctx)
+{
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
 	bpf_override_return(ctx, 123);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi_session_cookie.c b/tools/testing/selftests/bpf/progs/kprobe_multi_session_cookie.c
index 0835b5edf685..ad627016e3e5 100644
--- a/tools/testing/selftests/bpf/progs/kprobe_multi_session_cookie.c
+++ b/tools/testing/selftests/bpf/progs/kprobe_multi_session_cookie.c
@@ -1,9 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/bpf.h>
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include <stdbool.h>
-#include "bpf_kfuncs.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -23,16 +22,16 @@ int BPF_PROG(trigger)
 	return 0;
 }
 
-static int check_cookie(__u64 val, __u64 *result)
+static int check_cookie(struct pt_regs *ctx, __u64 val, __u64 *result)
 {
 	__u64 *cookie;
 
 	if (bpf_get_current_pid_tgid() >> 32 != pid)
 		return 1;
 
-	cookie = bpf_session_cookie();
+	cookie = bpf_session_cookie(ctx);
 
-	if (bpf_session_is_return())
+	if (bpf_session_is_return(ctx))
 		*result = *cookie == val ? val : 0;
 	else
 		*cookie = val;
@@ -42,17 +41,17 @@ static int check_cookie(__u64 val, __u64 *result)
 SEC("kprobe.session/bpf_fentry_test1")
 int test_kprobe_1(struct pt_regs *ctx)
 {
-	return check_cookie(1, &test_kprobe_1_result);
+	return check_cookie(ctx, 1, &test_kprobe_1_result);
 }
 
 SEC("kprobe.session/bpf_fentry_test1")
 int test_kprobe_2(struct pt_regs *ctx)
 {
-	return check_cookie(2, &test_kprobe_2_result);
+	return check_cookie(ctx, 2, &test_kprobe_2_result);
 }
 
 SEC("kprobe.session/bpf_fentry_test1")
 int test_kprobe_3(struct pt_regs *ctx)
 {
-	return check_cookie(3, &test_kprobe_3_result);
+	return check_cookie(ctx, 3, &test_kprobe_3_result);
 }
diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c
index 637e75df2e14..d0be77011a84 100644
--- a/tools/testing/selftests/bpf/progs/local_storage.c
+++ b/tools/testing/selftests/bpf/progs/local_storage.c
@@ -62,7 +62,6 @@ SEC("lsm/inode_unlink")
 int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim)
 {
 	__u32 pid = bpf_get_current_pid_tgid() >> 32;
-	struct bpf_local_storage *local_storage;
 	struct local_storage *storage;
 	struct task_struct *task;
 	bool is_self_unlink;
@@ -88,15 +87,10 @@ int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim)
 	if (!storage || storage->value)
 		return 0;
 
-	if (bpf_task_storage_delete(&task_storage_map, task))
+	if (bpf_task_storage_delete(&task_storage_map2, task))
 		return 0;
 
-	/* Ensure that the task_storage_map is disconnected from the storage.
-	 * The storage memory should not be freed back to the
-	 * bpf_mem_alloc.
-	 */
-	local_storage = task->bpf_storage;
-	if (!local_storage || local_storage->smap)
+	if (bpf_task_storage_delete(&task_storage_map, task))
 		return 0;
 
 	task_storage_result = 0;
@@ -164,18 +158,9 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address,
 	if (bpf_sk_storage_delete(&sk_storage_map2, sk))
 		return 0;
 
-	storage = bpf_sk_storage_get(&sk_storage_map2, sk, 0,
-				     BPF_LOCAL_STORAGE_GET_F_CREATE);
-	if (!storage)
-		return 0;
-
 	if (bpf_sk_storage_delete(&sk_storage_map, sk))
 		return 0;
 
-	/* Ensure that the sk_storage_map is disconnected from the storage. */
-	if (!sk->sk_bpf_storage || sk->sk_bpf_storage->smap)
-		return 0;
-
 	sk_storage_result = 0;
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/map_kptr.c b/tools/testing/selftests/bpf/progs/map_kptr.c
index edaba481db9d..e708ffbe1f61 100644
--- a/tools/testing/selftests/bpf/progs/map_kptr.c
+++ b/tools/testing/selftests/bpf/progs/map_kptr.c
@@ -487,6 +487,24 @@ int test_map_kptr_ref3(struct __sk_buff *ctx)
 	return 0;
 }
 
+int num_of_refs;
+
+SEC("syscall")
+int count_ref(void *ctx)
+{
+	struct prog_test_ref_kfunc *p;
+	unsigned long arg = 0;
+
+	p = bpf_kfunc_call_test_acquire(&arg);
+	if (!p)
+		return 1;
+
+	num_of_refs = p->cnt.refs.counter;
+
+	bpf_kfunc_call_test_release(p);
+	return 0;
+}
+
 SEC("syscall")
 int test_ls_map_kptr_ref1(void *ctx)
 {
diff --git a/tools/testing/selftests/bpf/progs/map_kptr_fail.c b/tools/testing/selftests/bpf/progs/map_kptr_fail.c
index 4c0ff01f1a96..6443b320c732 100644
--- a/tools/testing/selftests/bpf/progs/map_kptr_fail.c
+++ b/tools/testing/selftests/bpf/progs/map_kptr_fail.c
@@ -272,7 +272,7 @@ int reject_untrusted_xchg(struct __sk_buff *ctx)
 
 SEC("?tc")
 __failure
-__msg("invalid kptr access, R2 type=ptr_prog_test_ref_kfunc expected=ptr_prog_test_member")
+__msg("invalid kptr access, R2 type=trusted_ptr_prog_test_ref_kfunc expected=ptr_prog_test_member")
 int reject_bad_type_xchg(struct __sk_buff *ctx)
 {
 	struct prog_test_ref_kfunc *ref_ptr;
@@ -291,7 +291,7 @@ int reject_bad_type_xchg(struct __sk_buff *ctx)
 }
 
 SEC("?tc")
-__failure __msg("invalid kptr access, R2 type=ptr_prog_test_ref_kfunc")
+__failure __msg("invalid kptr access, R2 type=trusted_ptr_prog_test_ref_kfunc")
 int reject_member_of_ref_xchg(struct __sk_buff *ctx)
 {
 	struct prog_test_ref_kfunc *ref_ptr;
diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_array.c b/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
index 37c2d2608ec0..ed6a2a93d5a5 100644
--- a/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
+++ b/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
@@ -187,4 +187,36 @@ out:
 	return 0;
 }
 
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 2);
+	__type(key, int);
+	__type(value, u32);
+} percpu SEC(".maps");
+
+SEC("?fentry/bpf_fentry_test1")
+int BPF_PROG(test_percpu_array, int x)
+{
+	u64 value = 0xDEADC0DE;
+	int key = 0;
+
+	bpf_map_update_elem(&percpu, &key, &value, BPF_ANY);
+	return 0;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE);
+	__type(key, struct bpf_cgroup_storage_key);
+	__type(value, u32);
+} percpu_cgroup_storage SEC(".maps");
+
+SEC("cgroup_skb/egress")
+int cgroup_egress(struct __sk_buff *skb)
+{
+	u32 *val = bpf_get_local_storage(&percpu_cgroup_storage, 0);
+
+	*val = 1;
+	return 1;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/rbtree_fail.c b/tools/testing/selftests/bpf/progs/rbtree_fail.c
index 4acb6af2dfe3..70b7baf9304b 100644
--- a/tools/testing/selftests/bpf/progs/rbtree_fail.c
+++ b/tools/testing/selftests/bpf/progs/rbtree_fail.c
@@ -153,7 +153,7 @@ long rbtree_api_add_to_multiple_trees(void *ctx)
 }
 
 SEC("?tc")
-__failure __msg("dereference of modified ptr_or_null_ ptr R2 off=16 disallowed")
+__failure __msg("Possibly NULL pointer passed to trusted arg1")
 long rbtree_api_use_unchecked_remove_retval(void *ctx)
 {
 	struct bpf_rb_node *res;
diff --git a/tools/testing/selftests/bpf/progs/rcu_read_lock.c b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
index d70c28824bbe..b4e073168fb1 100644
--- a/tools/testing/selftests/bpf/progs/rcu_read_lock.c
+++ b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
@@ -7,6 +7,16 @@
 #include "bpf_tracing_net.h"
 #include "bpf_misc.h"
 
+/* clang considers 'sum += 1' as usage but 'sum++' as non-usage.  GCC
+ * is more consistent and considers both 'sum += 1' and 'sum++' as
+ * non-usage.  This triggers warnings in the functions below.
+ *
+ * Starting with GCC 16 -Wunused-but-set-variable=2 can be used to
+ * mimic clang's behavior.  */
+#if !defined(__clang__) && __GNUC__ > 15
+#pragma GCC diagnostic ignored "-Wunused-but-set-variable"
+#endif
+
 char _license[] SEC("license") = "GPL";
 
 struct {
diff --git a/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c b/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c
deleted file mode 100644
index 69da05bb6c63..000000000000
--- a/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c
+++ /dev/null
@@ -1,38 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2022. Huawei Technologies Co., Ltd */
-#include "vmlinux.h"
-#include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
-
-extern bool CONFIG_PREEMPTION __kconfig __weak;
-extern const int bpf_task_storage_busy __ksym;
-
-char _license[] SEC("license") = "GPL";
-
-int pid = 0;
-int busy = 0;
-
-struct {
-	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
-	__uint(map_flags, BPF_F_NO_PREALLOC);
-	__type(key, int);
-	__type(value, long);
-} task SEC(".maps");
-
-SEC("raw_tp/sys_enter")
-int BPF_PROG(read_bpf_task_storage_busy)
-{
-	int *value;
-
-	if (!CONFIG_PREEMPTION)
-		return 0;
-
-	if (bpf_get_current_pid_tgid() >> 32 != pid)
-		return 0;
-
-	value = bpf_this_cpu_ptr(&bpf_task_storage_busy);
-	if (value)
-		busy = *value;
-
-	return 0;
-}
diff --git a/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c b/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c
index 46d6eb2a3b17..c8f4815c8dfb 100644
--- a/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c
+++ b/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c
@@ -6,7 +6,6 @@
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_core_read.h>
 
-void *local_storage_ptr = NULL;
 void *sk_ptr = NULL;
 int cookie_found = 0;
 __u64 cookie = 0;
@@ -19,21 +18,17 @@ struct {
 	__type(value, int);
 } sk_storage SEC(".maps");
 
-SEC("fexit/bpf_local_storage_destroy")
-int BPF_PROG(bpf_local_storage_destroy, struct bpf_local_storage *local_storage)
+SEC("fexit/bpf_sk_storage_free")
+int BPF_PROG(bpf_sk_storage_free, struct sock *sk)
 {
-	struct sock *sk;
-
-	if (local_storage_ptr != local_storage)
+	if (sk_ptr != sk)
 		return 0;
 
-	sk = bpf_core_cast(sk_ptr, struct sock);
 	if (sk->sk_cookie.counter != cookie)
 		return 0;
 
 	cookie_found++;
 	omem = sk->sk_omem_alloc.counter;
-	local_storage_ptr = NULL;
 
 	return 0;
 }
@@ -50,7 +45,6 @@ int BPF_PROG(inet6_sock_destruct, struct sock *sk)
 	if (value && *value == 0xdeadbeef) {
 		cookie_found++;
 		sk_ptr = sk;
-		local_storage_ptr = sk->sk_bpf_storage;
 	}
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/stacktrace_ips.c b/tools/testing/selftests/bpf/progs/stacktrace_ips.c
index a96c8150d7f5..6830f2978613 100644
--- a/tools/testing/selftests/bpf/progs/stacktrace_ips.c
+++ b/tools/testing/selftests/bpf/progs/stacktrace_ips.c
@@ -31,6 +31,13 @@ int unused(void)
 
 __u32 stack_key;
 
+SEC("kprobe")
+int kprobe_test(struct pt_regs *ctx)
+{
+	stack_key = bpf_get_stackid(ctx, &stackmap, 0);
+	return 0;
+}
+
 SEC("kprobe.multi")
 int kprobe_multi_test(struct pt_regs *ctx)
 {
@@ -46,4 +53,24 @@ int rawtp_test(void *ctx)
 	return 0;
 }
 
+SEC("fentry/bpf_testmod_stacktrace_test")
+int fentry_test(struct pt_regs *ctx)
+{
+	/*
+	 * Skip 2 bpf_program/trampoline stack entries:
+	 * - bpf_prog_bd1f7a949f55fb03_fentry_test
+	 * - bpf_trampoline_182536277701
+	 */
+	stack_key = bpf_get_stackid(ctx, &stackmap, 2);
+	return 0;
+}
+
+SEC("fexit/bpf_testmod_stacktrace_test")
+int fexit_test(struct pt_regs *ctx)
+{
+	/* Skip 2 bpf_program/trampoline stack entries, check fentry_test. */
+	stack_key = bpf_get_stackid(ctx, &stackmap, 2);
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/stream.c b/tools/testing/selftests/bpf/progs/stream.c
index 4a5bd852f10c..6f999ba951a3 100644
--- a/tools/testing/selftests/bpf/progs/stream.c
+++ b/tools/testing/selftests/bpf/progs/stream.c
@@ -42,6 +42,10 @@ int size;
 u64 fault_addr;
 void *arena_ptr;
 
+#define private(name) SEC(".bss." #name) __hidden __attribute__((aligned(8)))
+
+private(STREAM) struct bpf_spin_lock block;
+
 SEC("syscall")
 __success __retval(0)
 int stream_exhaust(void *ctx)
@@ -234,4 +238,53 @@ int stream_arena_callback_fault(void *ctx)
 	return 0;
 }
 
+SEC("syscall")
+__arch_x86_64
+__arch_arm64
+__success __retval(0)
+__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}")
+__stderr("Call trace:\n"
+"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+"|[ \t]+[^\n]+\n)*}}")
+int stream_print_stack_kfunc(void *ctx)
+{
+	return bpf_stream_print_stack(BPF_STDERR);
+}
+
+SEC("syscall")
+__success __retval(-2)
+int stream_print_stack_invalid_id(void *ctx)
+{
+	/* Try to pass an invalid stream ID. */
+	return bpf_stream_print_stack((enum bpf_stream_id)0xbadcafe);
+}
+
+SEC("syscall")
+__arch_x86_64
+__arch_arm64
+__success __retval(0)
+__stdout(_STR)
+__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}")
+__stderr("Call trace:\n"
+"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+"|[ \t]+[^\n]+\n)*}}")
+int stream_print_kfuncs_locked(void *ctx)
+{
+	int ret;
+
+	bpf_spin_lock(&block);
+
+	ret = bpf_stream_printk(BPF_STDOUT, _STR);
+	if (ret)
+		goto out;
+
+	ret = bpf_stream_print_stack(BPF_STDERR);
+
+out:
+	bpf_spin_unlock(&block);
+
+	return ret;
+}
+
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/stream_fail.c b/tools/testing/selftests/bpf/progs/stream_fail.c
index 3662515f0107..8e8249f3521c 100644
--- a/tools/testing/selftests/bpf/progs/stream_fail.c
+++ b/tools/testing/selftests/bpf/progs/stream_fail.c
@@ -10,7 +10,7 @@ SEC("syscall")
 __failure __msg("Possibly NULL pointer passed")
 int stream_vprintk_null_arg(void *ctx)
 {
-	bpf_stream_vprintk_impl(BPF_STDOUT, "", NULL, 0, NULL);
+	bpf_stream_vprintk(BPF_STDOUT, "", NULL, 0);
 	return 0;
 }
 
@@ -18,7 +18,7 @@ SEC("syscall")
 __failure __msg("R3 type=scalar expected=")
 int stream_vprintk_scalar_arg(void *ctx)
 {
-	bpf_stream_vprintk_impl(BPF_STDOUT, "", (void *)46, 0, NULL);
+	bpf_stream_vprintk(BPF_STDOUT, "", (void *)46, 0);
 	return 0;
 }
 
@@ -26,7 +26,7 @@ SEC("syscall")
 __failure __msg("arg#1 doesn't point to a const string")
 int stream_vprintk_string_arg(void *ctx)
 {
-	bpf_stream_vprintk_impl(BPF_STDOUT, ctx, NULL, 0, NULL);
+	bpf_stream_vprintk(BPF_STDOUT, ctx, NULL, 0);
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c b/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c
index 826e6b6aff7e..bddc4e8579d2 100644
--- a/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c
+++ b/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c
@@ -33,6 +33,8 @@ SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_null1(void *ctx) { return
 SEC("syscall")  __retval(USER_PTR_ERR)int test_strcmp_null2(void *ctx) { return bpf_strcmp("hello", NULL); }
 SEC("syscall") __retval(USER_PTR_ERR) int test_strcasecmp_null1(void *ctx) { return bpf_strcasecmp(NULL, "HELLO"); }
 SEC("syscall")  __retval(USER_PTR_ERR)int test_strcasecmp_null2(void *ctx) { return bpf_strcasecmp("HELLO", NULL); }
+SEC("syscall") __retval(USER_PTR_ERR)int test_strncasecmp_null1(void *ctx) { return bpf_strncasecmp(NULL, "HELLO", 5); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strncasecmp_null2(void *ctx) { return bpf_strncasecmp("HELLO", NULL, 5);	 }
 SEC("syscall")  __retval(USER_PTR_ERR)int test_strchr_null(void *ctx) { return bpf_strchr(NULL, 'a'); }
 SEC("syscall")  __retval(USER_PTR_ERR)int test_strchrnul_null(void *ctx) { return bpf_strchrnul(NULL, 'a'); }
 SEC("syscall")  __retval(USER_PTR_ERR)int test_strnchr_null(void *ctx) { return bpf_strnchr(NULL, 1, 'a'); }
@@ -57,6 +59,8 @@ SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_user_ptr1(void *ctx) { ret
 SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_user_ptr2(void *ctx) { return bpf_strcmp("hello", user_ptr); }
 SEC("syscall") __retval(USER_PTR_ERR) int test_strcasecmp_user_ptr1(void *ctx) { return bpf_strcasecmp(user_ptr, "HELLO"); }
 SEC("syscall") __retval(USER_PTR_ERR) int test_strcasecmp_user_ptr2(void *ctx) { return bpf_strcasecmp("HELLO", user_ptr); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strncasecmp_user_ptr1(void *ctx) { return bpf_strncasecmp(user_ptr, "HELLO", 5); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strncasecmp_user_ptr2(void *ctx) { return bpf_strncasecmp("HELLO", user_ptr, 5);	 }
 SEC("syscall") __retval(USER_PTR_ERR) int test_strchr_user_ptr(void *ctx) { return bpf_strchr(user_ptr, 'a'); }
 SEC("syscall") __retval(USER_PTR_ERR) int test_strchrnul_user_ptr(void *ctx) { return bpf_strchrnul(user_ptr, 'a'); }
 SEC("syscall") __retval(USER_PTR_ERR) int test_strnchr_user_ptr(void *ctx) { return bpf_strnchr(user_ptr, 1, 'a'); }
@@ -83,6 +87,8 @@ SEC("syscall") __retval(-EFAULT) int test_strcmp_pagefault1(void *ctx) { return
 SEC("syscall") __retval(-EFAULT) int test_strcmp_pagefault2(void *ctx) { return bpf_strcmp("hello", invalid_kern_ptr); }
 SEC("syscall") __retval(-EFAULT) int test_strcasecmp_pagefault1(void *ctx) { return bpf_strcasecmp(invalid_kern_ptr, "HELLO"); }
 SEC("syscall") __retval(-EFAULT) int test_strcasecmp_pagefault2(void *ctx) { return bpf_strcasecmp("HELLO", invalid_kern_ptr); }
+SEC("syscall") __retval(-EFAULT) int test_strncasecmp_pagefault1(void *ctx) { return bpf_strncasecmp(invalid_kern_ptr, "HELLO", 5); }
+SEC("syscall") __retval(-EFAULT) int test_strncasecmp_pagefault2(void *ctx) { return bpf_strncasecmp("HELLO", invalid_kern_ptr, 5);	 }
 SEC("syscall") __retval(-EFAULT) int test_strchr_pagefault(void *ctx) { return bpf_strchr(invalid_kern_ptr, 'a'); }
 SEC("syscall") __retval(-EFAULT) int test_strchrnul_pagefault(void *ctx) { return bpf_strchrnul(invalid_kern_ptr, 'a'); }
 SEC("syscall") __retval(-EFAULT) int test_strnchr_pagefault(void *ctx) { return bpf_strnchr(invalid_kern_ptr, 1, 'a'); }
diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c b/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c
index 05e1da1f250f..412c53b87b18 100644
--- a/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c
+++ b/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c
@@ -8,6 +8,7 @@ char long_str[XATTR_SIZE_MAX + 1];
 
 SEC("syscall") int test_strcmp_too_long(void *ctx) { return bpf_strcmp(long_str, long_str); }
 SEC("syscall") int test_strcasecmp_too_long(void *ctx) { return bpf_strcasecmp(long_str, long_str); }
+SEC("syscall") int test_strncasecmp_too_long(void *ctx) { return bpf_strncasecmp(long_str, long_str, sizeof(long_str)); }
 SEC("syscall") int test_strchr_too_long(void *ctx) { return bpf_strchr(long_str, 'b'); }
 SEC("syscall") int test_strchrnul_too_long(void *ctx) { return bpf_strchrnul(long_str, 'b'); }
 SEC("syscall") int test_strnchr_too_long(void *ctx) { return bpf_strnchr(long_str, sizeof(long_str), 'b'); }
diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
index a8513964516b..f65b1226a81a 100644
--- a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
+++ b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
@@ -17,6 +17,13 @@ __test(0) int test_strcasecmp_eq2(void *ctx) { return bpf_strcasecmp(str, "HELLO
 __test(0) int test_strcasecmp_eq3(void *ctx) { return bpf_strcasecmp(str, "HELLO world"); }
 __test(1) int test_strcasecmp_neq1(void *ctx) { return bpf_strcasecmp(str, "hello"); }
 __test(1) int test_strcasecmp_neq2(void *ctx) { return bpf_strcasecmp(str, "HELLO"); }
+__test(0) int test_strncasecmp_eq1(void *ctx) { return bpf_strncasecmp(str, "hello world", 11); }
+__test(0) int test_strncasecmp_eq2(void *ctx) { return bpf_strncasecmp(str, "HELLO WORLD", 11); }
+__test(0) int test_strncasecmp_eq3(void *ctx) { return bpf_strncasecmp(str, "HELLO world", 11); }
+__test(0) int test_strncasecmp_eq4(void *ctx) { return bpf_strncasecmp(str, "hello", 5); }
+__test(0) int test_strncasecmp_eq5(void *ctx) { return bpf_strncasecmp(str, "hello world!", 11); }
+__test(-1) int test_strncasecmp_neq1(void *ctx) { return bpf_strncasecmp(str, "hello!", 6); }
+__test(1) int test_strncasecmp_neq2(void *ctx) { return bpf_strncasecmp(str, "abc", 3); }
 __test(1) int test_strchr_found(void *ctx) { return bpf_strchr(str, 'e'); }
 __test(11) int test_strchr_null(void *ctx) { return bpf_strchr(str, '\0'); }
 __test(-ENOENT) int test_strchr_notfound(void *ctx) { return bpf_strchr(str, 'x'); }
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_assoc.c b/tools/testing/selftests/bpf/progs/struct_ops_assoc.c
new file mode 100644
index 000000000000..68842e3f936b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_assoc.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+int test_pid;
+
+/* Programs associated with st_ops_map_a */
+
+#define MAP_A_MAGIC 1234
+int test_err_a;
+
+SEC("struct_ops")
+int BPF_PROG(test_1_a, struct st_ops_args *args)
+{
+	return MAP_A_MAGIC;
+}
+
+SEC("tp_btf/sys_enter")
+int BPF_PROG(sys_enter_prog_a, struct pt_regs *regs, long id)
+{
+	struct st_ops_args args = {};
+	struct task_struct *task;
+	int ret;
+
+	task = bpf_get_current_task_btf();
+	if (!test_pid || task->pid != test_pid)
+		return 0;
+
+	ret = bpf_kfunc_multi_st_ops_test_1_assoc(&args);
+	if (ret != MAP_A_MAGIC)
+		test_err_a++;
+
+	return 0;
+}
+
+SEC("syscall")
+int syscall_prog_a(void *ctx)
+{
+	struct st_ops_args args = {};
+	int ret;
+
+	ret = bpf_kfunc_multi_st_ops_test_1_assoc(&args);
+	if (ret != MAP_A_MAGIC)
+		test_err_a++;
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_multi_st_ops st_ops_map_a = {
+	.test_1 = (void *)test_1_a,
+};
+
+/* Programs associated with st_ops_map_b */
+
+#define MAP_B_MAGIC 5678
+int test_err_b;
+
+SEC("struct_ops")
+int BPF_PROG(test_1_b, struct st_ops_args *args)
+{
+	return MAP_B_MAGIC;
+}
+
+SEC("tp_btf/sys_enter")
+int BPF_PROG(sys_enter_prog_b, struct pt_regs *regs, long id)
+{
+	struct st_ops_args args = {};
+	struct task_struct *task;
+	int ret;
+
+	task = bpf_get_current_task_btf();
+	if (!test_pid || task->pid != test_pid)
+		return 0;
+
+	ret = bpf_kfunc_multi_st_ops_test_1_assoc(&args);
+	if (ret != MAP_B_MAGIC)
+		test_err_b++;
+
+	return 0;
+}
+
+SEC("syscall")
+int syscall_prog_b(void *ctx)
+{
+	struct st_ops_args args = {};
+	int ret;
+
+	ret = bpf_kfunc_multi_st_ops_test_1_assoc(&args);
+	if (ret != MAP_B_MAGIC)
+		test_err_b++;
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_multi_st_ops st_ops_map_b = {
+	.test_1 = (void *)test_1_b,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_assoc_in_timer.c b/tools/testing/selftests/bpf/progs/struct_ops_assoc_in_timer.c
new file mode 100644
index 000000000000..0bed49e9f217
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_assoc_in_timer.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct elem {
+	struct bpf_timer timer;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} array_map SEC(".maps");
+
+#define MAP_MAGIC 1234
+int recur;
+int test_err;
+int timer_ns;
+int timer_test_1_ret;
+int timer_cb_run;
+
+__noinline static int timer_cb(void *map, int *key, struct bpf_timer *timer)
+{
+	struct st_ops_args args = {};
+
+	recur++;
+	timer_test_1_ret = bpf_kfunc_multi_st_ops_test_1_assoc(&args);
+	recur--;
+
+	timer_cb_run++;
+
+	return 0;
+}
+
+SEC("struct_ops")
+int BPF_PROG(test_1, struct st_ops_args *args)
+{
+	struct bpf_timer *timer;
+	int key = 0;
+
+	if (!recur) {
+		timer = bpf_map_lookup_elem(&array_map, &key);
+		if (!timer)
+			return 0;
+
+		bpf_timer_init(timer, &array_map, 1);
+		bpf_timer_set_callback(timer, timer_cb);
+		bpf_timer_start(timer, timer_ns, 0);
+	}
+
+	return MAP_MAGIC;
+}
+
+SEC("syscall")
+int syscall_prog(void *ctx)
+{
+	struct st_ops_args args = {};
+	int ret;
+
+	ret = bpf_kfunc_multi_st_ops_test_1_assoc(&args);
+	if (ret != MAP_MAGIC)
+		test_err++;
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_multi_st_ops st_ops_map = {
+	.test_1 = (void *)test_1,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_assoc_reuse.c b/tools/testing/selftests/bpf/progs/struct_ops_assoc_reuse.c
new file mode 100644
index 000000000000..396b3e58c729
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_assoc_reuse.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define MAP_A_MAGIC 1234
+int test_err_a;
+int recur;
+
+/*
+ * test_1_a is reused. The kfunc should not be able to get the associated
+ * struct_ops and call test_1 recursively as it is ambiguous.
+ */
+SEC("struct_ops")
+int BPF_PROG(test_1_a, struct st_ops_args *args)
+{
+	int ret;
+
+	if (!recur) {
+		recur++;
+		ret = bpf_kfunc_multi_st_ops_test_1_assoc(args);
+		if (ret != -1)
+			test_err_a++;
+		recur--;
+	}
+
+	return MAP_A_MAGIC;
+}
+
+/* Programs associated with st_ops_map_a */
+
+SEC("syscall")
+int syscall_prog_a(void *ctx)
+{
+	struct st_ops_args args = {};
+	int ret;
+
+	ret = bpf_kfunc_multi_st_ops_test_1_assoc(&args);
+	if (ret != MAP_A_MAGIC)
+		test_err_a++;
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_multi_st_ops st_ops_map_a = {
+	.test_1 = (void *)test_1_a,
+};
+
+/* Programs associated with st_ops_map_b */
+
+int test_err_b;
+
+SEC("syscall")
+int syscall_prog_b(void *ctx)
+{
+	struct st_ops_args args = {};
+	int ret;
+
+	ret = bpf_kfunc_multi_st_ops_test_1_assoc(&args);
+	if (ret != MAP_A_MAGIC)
+		test_err_b++;
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_multi_st_ops st_ops_map_b = {
+	.test_1 = (void *)test_1_a,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__wrong_type.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__wrong_type.c
index 6a2dd5367802..c8d217e89eea 100644
--- a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__wrong_type.c
+++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__wrong_type.c
@@ -12,7 +12,7 @@ void bpf_task_release(struct task_struct *p) __ksym;
  * reject programs returning a referenced kptr of the wrong type.
  */
 SEC("struct_ops/test_return_ref_kptr")
-__failure __msg("At program exit the register R0 is not a known value (ptr_or_null_)")
+__failure __msg("At program exit the register R0 is not a known value (trusted_ptr_or_null_)")
 struct task_struct *BPF_PROG(kptr_return_fail__wrong_type, int dummy,
 			     struct task_struct *task, struct cgroup *cgrp)
 {
diff --git a/tools/testing/selftests/bpf/progs/tailcall_sleepable.c b/tools/testing/selftests/bpf/progs/tailcall_sleepable.c
new file mode 100644
index 000000000000..d959a9eaaa9c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_sleepable.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "bpf_test_utils.h"
+
+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");
+
+SEC("?uprobe")
+int uprobe_normal(void *ctx)
+{
+	bpf_tail_call_static(ctx, &jmp_table, 0);
+	return 0;
+}
+
+SEC("?uprobe.s")
+int uprobe_sleepable_1(void *ctx)
+{
+	bpf_tail_call_static(ctx, &jmp_table, 0);
+	return 0;
+}
+
+int executed = 0;
+int my_pid = 0;
+
+SEC("?uprobe.s")
+int uprobe_sleepable_2(void *ctx)
+{
+	int pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != my_pid)
+		return 0;
+
+	executed++;
+	return 0;
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/task_local_data.bpf.h b/tools/testing/selftests/bpf/progs/task_local_data.bpf.h
index 432fff2af844..fed53d63a7e5 100644
--- a/tools/testing/selftests/bpf/progs/task_local_data.bpf.h
+++ b/tools/testing/selftests/bpf/progs/task_local_data.bpf.h
@@ -80,7 +80,7 @@ struct tld_metadata {
 };
 
 struct tld_meta_u {
-	__u8 cnt;
+	__u16 cnt;
 	__u16 size;
 	struct tld_metadata metadata[TLD_MAX_DATA_CNT];
 };
diff --git a/tools/testing/selftests/bpf/progs/task_ls_recursion.c b/tools/testing/selftests/bpf/progs/task_ls_recursion.c
index f1853c38aada..b37359432692 100644
--- a/tools/testing/selftests/bpf/progs/task_ls_recursion.c
+++ b/tools/testing/selftests/bpf/progs/task_ls_recursion.c
@@ -36,14 +36,9 @@ int BPF_PROG(on_update)
 	if (!test_pid || task->pid != test_pid)
 		return 0;
 
+	/* This will succeed as there is no real deadlock */
 	ptr = bpf_task_storage_get(&map_a, task, 0,
 				   BPF_LOCAL_STORAGE_GET_F_CREATE);
-	/* ptr will not be NULL when it is called from
-	 * the bpf_task_storage_get(&map_b,...F_CREATE) in
-	 * the BPF_PROG(on_enter) below.  It is because
-	 * the value can be found in map_a and the kernel
-	 * does not need to acquire any spin_lock.
-	 */
 	if (ptr) {
 		int err;
 
@@ -53,12 +48,7 @@ int BPF_PROG(on_update)
 			nr_del_errs++;
 	}
 
-	/* This will still fail because map_b is empty and
-	 * this BPF_PROG(on_update) has failed to acquire
-	 * the percpu busy lock => meaning potential
-	 * deadlock is detected and it will fail to create
-	 * new storage.
-	 */
+	/* This will succeed as there is no real deadlock */
 	ptr = bpf_task_storage_get(&map_b, task, 0,
 				   BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (ptr)
diff --git a/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c b/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c
index 986829aaf73a..6ce98fe9f387 100644
--- a/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c
+++ b/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c
@@ -1,15 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include "vmlinux.h"
+#include <errno.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
-#ifndef EBUSY
-#define EBUSY 16
-#endif
-
 extern bool CONFIG_PREEMPTION __kconfig __weak;
 int nr_get_errs = 0;
 int nr_del_errs = 0;
@@ -40,7 +37,7 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
 
 	ret = bpf_task_storage_delete(&task_storage,
 				      bpf_get_current_task_btf());
-	if (ret == -EBUSY)
+	if (ret == -EDEADLK || ret == -ETIMEDOUT)
 		__sync_fetch_and_add(&nr_del_errs, 1);
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/task_work.c b/tools/testing/selftests/bpf/progs/task_work.c
index 663a80990f8f..a6009d105158 100644
--- a/tools/testing/selftests/bpf/progs/task_work.c
+++ b/tools/testing/selftests/bpf/progs/task_work.c
@@ -65,8 +65,7 @@ int oncpu_hash_map(struct pt_regs *args)
 	work = bpf_map_lookup_elem(&hmap, &key);
 	if (!work)
 		return 0;
-
-	bpf_task_work_schedule_resume_impl(task, &work->tw, &hmap, process_work, NULL);
+	bpf_task_work_schedule_resume(task, &work->tw, &hmap, process_work);
 	return 0;
 }
 
@@ -80,7 +79,7 @@ int oncpu_array_map(struct pt_regs *args)
 	work = bpf_map_lookup_elem(&arrmap, &key);
 	if (!work)
 		return 0;
-	bpf_task_work_schedule_signal_impl(task, &work->tw, &arrmap, process_work, NULL);
+	bpf_task_work_schedule_signal(task, &work->tw, &arrmap, process_work);
 	return 0;
 }
 
@@ -102,6 +101,6 @@ int oncpu_lru_map(struct pt_regs *args)
 	work = bpf_map_lookup_elem(&lrumap, &key);
 	if (!work || work->data[0])
 		return 0;
-	bpf_task_work_schedule_resume_impl(task, &work->tw, &lrumap, process_work, NULL);
+	bpf_task_work_schedule_resume(task, &work->tw, &lrumap, process_work);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/task_work_fail.c b/tools/testing/selftests/bpf/progs/task_work_fail.c
index 1270953fd092..82e4b8913333 100644
--- a/tools/testing/selftests/bpf/progs/task_work_fail.c
+++ b/tools/testing/selftests/bpf/progs/task_work_fail.c
@@ -53,7 +53,7 @@ int mismatch_map(struct pt_regs *args)
 	work = bpf_map_lookup_elem(&arrmap, &key);
 	if (!work)
 		return 0;
-	bpf_task_work_schedule_resume_impl(task, &work->tw, &hmap, process_work, NULL);
+	bpf_task_work_schedule_resume(task, &work->tw, &hmap, process_work);
 	return 0;
 }
 
@@ -65,7 +65,7 @@ int no_map_task_work(struct pt_regs *args)
 	struct bpf_task_work tw;
 
 	task = bpf_get_current_task_btf();
-	bpf_task_work_schedule_resume_impl(task, &tw, &hmap, process_work, NULL);
+	bpf_task_work_schedule_resume(task, &tw, &hmap, process_work);
 	return 0;
 }
 
@@ -76,7 +76,7 @@ int task_work_null(struct pt_regs *args)
 	struct task_struct *task;
 
 	task = bpf_get_current_task_btf();
-	bpf_task_work_schedule_resume_impl(task, NULL, &hmap, process_work, NULL);
+	bpf_task_work_schedule_resume(task, NULL, &hmap, process_work);
 	return 0;
 }
 
@@ -91,6 +91,6 @@ int map_null(struct pt_regs *args)
 	work = bpf_map_lookup_elem(&arrmap, &key);
 	if (!work)
 		return 0;
-	bpf_task_work_schedule_resume_impl(task, &work->tw, NULL, process_work, NULL);
+	bpf_task_work_schedule_resume(task, &work->tw, NULL, process_work);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/task_work_stress.c b/tools/testing/selftests/bpf/progs/task_work_stress.c
index 55e555f7f41b..1d4378f351ef 100644
--- a/tools/testing/selftests/bpf/progs/task_work_stress.c
+++ b/tools/testing/selftests/bpf/progs/task_work_stress.c
@@ -51,8 +51,8 @@ int schedule_task_work(void *ctx)
 		if (!work)
 			return 0;
 	}
-	err = bpf_task_work_schedule_signal_impl(bpf_get_current_task_btf(), &work->tw, &hmap,
-						 process_work, NULL);
+	err = bpf_task_work_schedule_signal(bpf_get_current_task_btf(), &work->tw, &hmap,
+					    process_work);
 	if (err)
 		__sync_fetch_and_add(&schedule_error, 1);
 	else
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c
index f7b330ddd007..076fbf03a126 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_nf.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c
@@ -15,7 +15,6 @@
 
 extern unsigned long CONFIG_HZ __kconfig;
 
-int test_einval_bpf_tuple = 0;
 int test_einval_reserved = 0;
 int test_einval_reserved_new = 0;
 int test_einval_netns_id = 0;
@@ -99,12 +98,6 @@ nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32,
 
 	__builtin_memset(&bpf_tuple, 0, sizeof(bpf_tuple.ipv4));
 
-	ct = lookup_fn(ctx, NULL, 0, &opts_def, sizeof(opts_def));
-	if (ct)
-		bpf_ct_release(ct);
-	else
-		test_einval_bpf_tuple = opts_def.error;
-
 	opts_def.reserved[0] = 1;
 	ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def,
 		       sizeof(opts_def));
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c b/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c
index a586f087ffeb..2c156cd166af 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c
@@ -4,6 +4,7 @@
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
 
 struct nf_conn;
 
@@ -18,6 +19,10 @@ struct nf_conn *bpf_skb_ct_alloc(struct __sk_buff *, struct bpf_sock_tuple *, u3
 				 struct bpf_ct_opts___local *, u32) __ksym;
 struct nf_conn *bpf_skb_ct_lookup(struct __sk_buff *, struct bpf_sock_tuple *, u32,
 				  struct bpf_ct_opts___local *, u32) __ksym;
+struct nf_conn *bpf_xdp_ct_alloc(struct xdp_md *, struct bpf_sock_tuple *, u32,
+				 struct bpf_ct_opts___local *, u32) __ksym;
+struct nf_conn *bpf_xdp_ct_lookup(struct xdp_md *, struct bpf_sock_tuple *, u32,
+				  struct bpf_ct_opts___local *, u32) __ksym;
 struct nf_conn *bpf_ct_insert_entry(struct nf_conn *) __ksym;
 void bpf_ct_release(struct nf_conn *) __ksym;
 void bpf_ct_set_timeout(struct nf_conn *, u32) __ksym;
@@ -146,4 +151,56 @@ int change_status_after_alloc(struct __sk_buff *ctx)
 	return 0;
 }
 
+SEC("?tc")
+__failure __msg("Possibly NULL pointer passed to trusted arg1")
+int lookup_null_bpf_tuple(struct __sk_buff *ctx)
+{
+	struct bpf_ct_opts___local opts = {};
+	struct nf_conn *ct;
+
+	ct = bpf_skb_ct_lookup(ctx, NULL, 0, &opts, sizeof(opts));
+	if (ct)
+		bpf_ct_release(ct);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("Possibly NULL pointer passed to trusted arg3")
+int lookup_null_bpf_opts(struct __sk_buff *ctx)
+{
+	struct bpf_sock_tuple tup = {};
+	struct nf_conn *ct;
+
+	ct = bpf_skb_ct_lookup(ctx, &tup, sizeof(tup.ipv4), NULL, sizeof(struct bpf_ct_opts___local));
+	if (ct)
+		bpf_ct_release(ct);
+	return 0;
+}
+
+SEC("?xdp")
+__failure __msg("Possibly NULL pointer passed to trusted arg1")
+int xdp_lookup_null_bpf_tuple(struct xdp_md *ctx)
+{
+	struct bpf_ct_opts___local opts = {};
+	struct nf_conn *ct;
+
+	ct = bpf_xdp_ct_lookup(ctx, NULL, 0, &opts, sizeof(opts));
+	if (ct)
+		bpf_ct_release(ct);
+	return 0;
+}
+
+SEC("?xdp")
+__failure __msg("Possibly NULL pointer passed to trusted arg3")
+int xdp_lookup_null_bpf_opts(struct xdp_md *ctx)
+{
+	struct bpf_sock_tuple tup = {};
+	struct nf_conn *ct;
+
+	ct = bpf_xdp_ct_lookup(ctx, &tup, sizeof(tup.ipv4), NULL, sizeof(struct bpf_ct_opts___local));
+	if (ct)
+		bpf_ct_release(ct);
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_btf_decl_tag.c b/tools/testing/selftests/bpf/progs/test_btf_decl_tag.c
index c88ccc53529a..0c3df19626cb 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_decl_tag.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_decl_tag.c
@@ -33,7 +33,7 @@ struct {
 } hashmap1 SEC(".maps");
 
 
-static __noinline int foo(int x __tag1 __tag2) __tag1 __tag2
+static __noinline __tag1 __tag2 int foo(int x __tag1 __tag2)
 {
 	struct key_t key;
 	value_t val = {};
diff --git a/tools/testing/selftests/bpf/progs/test_ctx.c b/tools/testing/selftests/bpf/progs/test_ctx.c
new file mode 100644
index 000000000000..7d4995506717
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ctx.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2026 Valve Corporation.
+ * Author: Changwoo Min <changwoo@igalia.com>
+ */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+extern void bpf_kfunc_trigger_ctx_check(void) __ksym;
+
+int count_hardirq;
+int count_softirq;
+int count_task;
+
+/* Triggered via bpf_prog_test_run from user-space */
+SEC("syscall")
+int trigger_all_contexts(void *ctx)
+{
+	if (bpf_in_task())
+		__sync_fetch_and_add(&count_task, 1);
+
+	/* Trigger the firing of a hardirq and softirq for test. */
+	bpf_kfunc_trigger_ctx_check();
+	return 0;
+}
+
+/* Observer for HardIRQ */
+SEC("fentry/bpf_testmod_test_hardirq_fn")
+int BPF_PROG(on_hardirq)
+{
+	if (bpf_in_hardirq())
+		__sync_fetch_and_add(&count_hardirq, 1);
+	return 0;
+}
+
+/* Observer for SoftIRQ */
+SEC("fentry/bpf_testmod_test_softirq_fn")
+int BPF_PROG(on_softirq)
+{
+	if (bpf_in_serving_softirq())
+		__sync_fetch_and_add(&count_softirq, 1);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c
index 061befb004c2..d249113ed657 100644
--- a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c
+++ b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c
@@ -48,10 +48,9 @@ SEC("?lsm.s/bpf")
 __failure __msg("arg#0 expected pointer to stack or const struct bpf_dynptr")
 int BPF_PROG(not_ptr_to_stack, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
 {
-	unsigned long val = 0;
+	static struct bpf_dynptr val;
 
-	return bpf_verify_pkcs7_signature((struct bpf_dynptr *)val,
-					  (struct bpf_dynptr *)val, NULL);
+	return bpf_verify_pkcs7_signature(&val, &val, NULL);
 }
 
 SEC("lsm.s/bpf")
diff --git a/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c b/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c
index 0ad1bf1ede8d..967081bbcfe1 100644
--- a/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c
+++ b/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c
@@ -29,7 +29,7 @@ int kfunc_dynptr_nullable_test2(struct __sk_buff *skb)
 }
 
 SEC("tc")
-__failure __msg("expected pointer to stack or const struct bpf_dynptr")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
 int kfunc_dynptr_nullable_test3(struct __sk_buff *skb)
 {
 	struct bpf_dynptr data;
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c b/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c
index 69aacc96db36..ef9edca184ea 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c
@@ -44,4 +44,18 @@ int prog_skb_parser(struct __sk_buff *skb)
 	return SK_PASS;
 }
 
+SEC("sk_skb/stream_verdict")
+int prog_skb_verdict_ingress(struct __sk_buff *skb)
+{
+	int one = 1;
+
+	return bpf_sk_redirect_map(skb, &sock_map_rx, one, BPF_F_INGRESS);
+}
+
+SEC("sk_skb/stream_parser")
+int prog_skb_verdict_ingress_strp(struct __sk_buff *skb)
+{
+	return skb->len;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
index 7330c61b5730..7376df405a6b 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
@@ -23,7 +23,12 @@ static const int cfg_udp_src = 20000;
 	(((__u64)len & BPF_ADJ_ROOM_ENCAP_L2_MASK)	\
 	 << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
 
-#define	L2_PAD_SZ	(sizeof(struct vxlanhdr) + ETH_HLEN)
+struct vxlanhdr___local {
+	__be32 vx_flags;
+	__be32 vx_vni;
+};
+
+#define	L2_PAD_SZ	(sizeof(struct vxlanhdr___local) + ETH_HLEN)
 
 #define	UDP_PORT		5555
 #define	MPLS_OVER_UDP_PORT	6635
@@ -154,7 +159,7 @@ static __always_inline int __encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
 		l2_len = ETH_HLEN;
 		if (ext_proto & EXTPROTO_VXLAN) {
 			udp_dst = VXLAN_UDP_PORT;
-			l2_len += sizeof(struct vxlanhdr);
+			l2_len += sizeof(struct vxlanhdr___local);
 		} else
 			udp_dst = ETH_OVER_UDP_PORT;
 		break;
@@ -195,12 +200,12 @@ static __always_inline int __encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
 		flags |= BPF_F_ADJ_ROOM_ENCAP_L2_ETH;
 
 		if (ext_proto & EXTPROTO_VXLAN) {
-			struct vxlanhdr *vxlan_hdr = (struct vxlanhdr *)l2_hdr;
+			struct vxlanhdr___local *vxlan_hdr = (struct vxlanhdr___local *)l2_hdr;
 
 			vxlan_hdr->vx_flags = VXLAN_FLAGS;
 			vxlan_hdr->vx_vni = VXLAN_VNI;
 
-			l2_hdr += sizeof(struct vxlanhdr);
+			l2_hdr += sizeof(struct vxlanhdr___local);
 		}
 
 		if (bpf_skb_load_bytes(skb, 0, l2_hdr, ETH_HLEN))
@@ -285,7 +290,7 @@ static __always_inline int __encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
 		l2_len = ETH_HLEN;
 		if (ext_proto & EXTPROTO_VXLAN) {
 			udp_dst = VXLAN_UDP_PORT;
-			l2_len += sizeof(struct vxlanhdr);
+			l2_len += sizeof(struct vxlanhdr___local);
 		} else
 			udp_dst = ETH_OVER_UDP_PORT;
 		break;
@@ -325,12 +330,12 @@ static __always_inline int __encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
 		flags |= BPF_F_ADJ_ROOM_ENCAP_L2_ETH;
 
 		if (ext_proto & EXTPROTO_VXLAN) {
-			struct vxlanhdr *vxlan_hdr = (struct vxlanhdr *)l2_hdr;
+			struct vxlanhdr___local *vxlan_hdr = (struct vxlanhdr___local *)l2_hdr;
 
 			vxlan_hdr->vx_flags = VXLAN_FLAGS;
 			vxlan_hdr->vx_vni = VXLAN_VNI;
 
-			l2_hdr += sizeof(struct vxlanhdr);
+			l2_hdr += sizeof(struct vxlanhdr___local);
 		}
 
 		if (bpf_skb_load_bytes(skb, 0, l2_hdr, ETH_HLEN))
@@ -639,7 +644,7 @@ static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 			olen += ETH_HLEN;
 			break;
 		case VXLAN_UDP_PORT:
-			olen += ETH_HLEN + sizeof(struct vxlanhdr);
+			olen += ETH_HLEN + sizeof(struct vxlanhdr___local);
 			break;
 		}
 		break;
diff --git a/tools/testing/selftests/bpf/progs/timer.c b/tools/testing/selftests/bpf/progs/timer.c
index 4c677c001258..d6d5fefcd9b1 100644
--- a/tools/testing/selftests/bpf/progs/timer.c
+++ b/tools/testing/selftests/bpf/progs/timer.c
@@ -1,13 +1,17 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2021 Facebook */
-#include <linux/bpf.h>
-#include <time.h>
+
+#include <vmlinux.h>
 #include <stdbool.h>
 #include <errno.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
+#define CLOCK_MONOTONIC 1
+#define CLOCK_BOOTTIME 7
+
 char _license[] SEC("license") = "GPL";
+
 struct hmap_elem {
 	int counter;
 	struct bpf_timer timer;
@@ -59,10 +63,14 @@ __u64 bss_data;
 __u64 abs_data;
 __u64 err;
 __u64 ok;
+__u64 test_hits;
+__u64 update_hits;
+__u64 cancel_hits;
 __u64 callback_check = 52;
 __u64 callback2_check = 52;
 __u64 pinned_callback_check;
 __s32 pinned_cpu;
+bool async_cancel = 0;
 
 #define ARRAY 1
 #define HTAB 2
@@ -164,6 +172,29 @@ int BPF_PROG2(test1, int, a)
 	return 0;
 }
 
+static int timer_error(void *map, int *key, struct bpf_timer *timer)
+{
+	err = 42;
+	return 0;
+}
+
+SEC("syscall")
+int test_async_cancel_succeed(void *ctx)
+{
+	struct bpf_timer *arr_timer;
+	int array_key = ARRAY;
+
+	arr_timer = bpf_map_lookup_elem(&array, &array_key);
+	if (!arr_timer)
+		return 0;
+	bpf_timer_init(arr_timer, &array, CLOCK_MONOTONIC);
+	bpf_timer_set_callback(arr_timer, timer_error);
+	bpf_timer_start(arr_timer, 100000 /* 100us */, 0);
+	bpf_timer_cancel_async(arr_timer);
+	ok = 7;
+	return 0;
+}
+
 /* callback for prealloc and non-prealloca hashtab timers */
 static int timer_cb2(void *map, int *key, struct hmap_elem *val)
 {
@@ -399,27 +430,88 @@ static int race_timer_callback(void *race_array, int *race_key, struct bpf_timer
 	return 0;
 }
 
-SEC("syscall")
-int race(void *ctx)
+/* Callback that updates its own map element */
+static int update_self_callback(void *map, int *key, struct bpf_timer *timer)
+{
+	struct elem init = {};
+
+	bpf_map_update_elem(map, key, &init, BPF_ANY);
+	__sync_fetch_and_add(&update_hits, 1);
+	return 0;
+}
+
+/* Callback that cancels itself using async cancel */
+static int cancel_self_callback(void *map, int *key, struct bpf_timer *timer)
+{
+	bpf_timer_cancel_async(timer);
+	__sync_fetch_and_add(&cancel_hits, 1);
+	return 0;
+}
+
+enum test_mode {
+	TEST_RACE_SYNC,
+	TEST_RACE_ASYNC,
+	TEST_UPDATE,
+	TEST_CANCEL,
+};
+
+static __always_inline int test_common(enum test_mode mode)
 {
 	struct bpf_timer *timer;
-	int err, race_key = 0;
 	struct elem init;
+	int ret, key = 0;
 
 	__builtin_memset(&init, 0, sizeof(struct elem));
-	bpf_map_update_elem(&race_array, &race_key, &init, BPF_ANY);
 
-	timer = bpf_map_lookup_elem(&race_array, &race_key);
+	bpf_map_update_elem(&race_array, &key, &init, BPF_ANY);
+	timer = bpf_map_lookup_elem(&race_array, &key);
 	if (!timer)
-		return 1;
+		return 0;
 
-	err = bpf_timer_init(timer, &race_array, CLOCK_MONOTONIC);
-	if (err && err != -EBUSY)
-		return 1;
+	ret = bpf_timer_init(timer, &race_array, CLOCK_MONOTONIC);
+	if (ret && ret != -EBUSY)
+		return 0;
+
+	if (mode == TEST_RACE_SYNC || mode == TEST_RACE_ASYNC)
+		bpf_timer_set_callback(timer, race_timer_callback);
+	else if (mode == TEST_UPDATE)
+		bpf_timer_set_callback(timer, update_self_callback);
+	else
+		bpf_timer_set_callback(timer, cancel_self_callback);
 
-	bpf_timer_set_callback(timer, race_timer_callback);
 	bpf_timer_start(timer, 0, 0);
-	bpf_timer_cancel(timer);
+
+	if (mode == TEST_RACE_ASYNC)
+		bpf_timer_cancel_async(timer);
+	else if (mode == TEST_RACE_SYNC)
+		bpf_timer_cancel(timer);
 
 	return 0;
 }
+
+SEC("syscall")
+int race(void *ctx)
+{
+	return test_common(async_cancel ? TEST_RACE_ASYNC : TEST_RACE_SYNC);
+}
+
+SEC("perf_event")
+int nmi_race(void *ctx)
+{
+	__sync_fetch_and_add(&test_hits, 1);
+	return test_common(TEST_RACE_ASYNC);
+}
+
+SEC("perf_event")
+int nmi_update(void *ctx)
+{
+	__sync_fetch_and_add(&test_hits, 1);
+	return test_common(TEST_UPDATE);
+}
+
+SEC("perf_event")
+int nmi_cancel(void *ctx)
+{
+	__sync_fetch_and_add(&test_hits, 1);
+	return test_common(TEST_CANCEL);
+}
diff --git a/tools/testing/selftests/bpf/progs/timer_start_deadlock.c b/tools/testing/selftests/bpf/progs/timer_start_deadlock.c
new file mode 100644
index 000000000000..019518ee18cd
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/timer_start_deadlock.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define CLOCK_MONOTONIC 1
+
+char _license[] SEC("license") = "GPL";
+
+struct elem {
+	struct bpf_timer timer;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} timer_map SEC(".maps");
+
+volatile int in_timer_start;
+volatile int tp_called;
+
+static int timer_cb(void *map, int *key, struct elem *value)
+{
+	return 0;
+}
+
+SEC("tp_btf/hrtimer_cancel")
+int BPF_PROG(tp_hrtimer_cancel, struct hrtimer *hrtimer)
+{
+	struct bpf_timer *timer;
+	int key = 0;
+
+	if (!in_timer_start)
+		return 0;
+
+	tp_called = 1;
+	timer = bpf_map_lookup_elem(&timer_map, &key);
+
+	/*
+	 * Call bpf_timer_start() from the tracepoint within hrtimer logic
+	 * on the same timer to make sure it doesn't deadlock.
+	 */
+	bpf_timer_start(timer, 1000000000, 0);
+	return 0;
+}
+
+SEC("syscall")
+int start_timer(void *ctx)
+{
+	struct bpf_timer *timer;
+	int key = 0;
+
+	timer = bpf_map_lookup_elem(&timer_map, &key);
+	/* claude may complain here that there is no NULL check. Ignoring it. */
+	bpf_timer_init(timer, &timer_map, CLOCK_MONOTONIC);
+	bpf_timer_set_callback(timer, timer_cb);
+
+	/*
+	 * call hrtimer_start() twice, so that 2nd call does
+	 * remove_hrtimer() and trace_hrtimer_cancel() tracepoint.
+	 */
+	in_timer_start = 1;
+	bpf_timer_start(timer, 1000000000, 0);
+	bpf_timer_start(timer, 1000000000, 0);
+	in_timer_start = 0;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/timer_start_delete_race.c b/tools/testing/selftests/bpf/progs/timer_start_delete_race.c
new file mode 100644
index 000000000000..2ff6357f33f9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/timer_start_delete_race.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <linux/bpf.h>
+#include <time.h>
+#include <bpf/bpf_helpers.h>
+
+#define ITER_CNT 2000
+
+struct map_value {
+	struct bpf_timer timer;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+} timer_map SEC(".maps");
+
+long cb_cnt;
+
+/*
+ * Timer callback that accesses the map value.
+ * If the race bug exists and this runs on freed memory,
+ * KASAN should detect it.
+ */
+static int timer_cb(void *map, int *key, struct map_value *value)
+{
+	__sync_fetch_and_add(&cb_cnt, 1);
+	return 0;
+}
+
+SEC("syscall")
+int start_timer(void *ctx)
+{
+	struct map_value *value;
+	int i;
+
+	for (i = 0; i < ITER_CNT; i++) {
+		int key = 0;
+
+		value = bpf_map_lookup_elem(&timer_map, &key);
+		/* hey claude, no if (!value) here. The verifier got smarter */
+
+		bpf_timer_init(&value->timer, &timer_map, CLOCK_MONOTONIC);
+		bpf_timer_set_callback(&value->timer, timer_cb);
+		bpf_timer_start(&value->timer, 100000000, 0);
+	}
+	return 0;
+}
+
+SEC("syscall")
+int delete_elem(void *ctx)
+{
+	int i;
+
+	for (i = 0; i < ITER_CNT; i++) {
+		int key = 0;
+
+		bpf_map_delete_elem(&timer_map, &key);
+	}
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c
index 2898b3749d07..4ea0422d1042 100644
--- a/tools/testing/selftests/bpf/progs/trigger_bench.c
+++ b/tools/testing/selftests/bpf/progs/trigger_bench.c
@@ -25,6 +25,34 @@ static __always_inline void inc_counter(void)
 	__sync_add_and_fetch(&hits[cpu & CPU_MASK].value, 1);
 }
 
+volatile const int stacktrace;
+
+typedef __u64 stack_trace_t[128];
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	 __uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, stack_trace_t);
+} stack_heap SEC(".maps");
+
+static __always_inline void do_stacktrace(void *ctx)
+{
+	if (!stacktrace)
+		return;
+
+	__u64 *ptr = bpf_map_lookup_elem(&stack_heap, &(__u32){0});
+
+	if (ptr)
+		bpf_get_stack(ctx, ptr, sizeof(stack_trace_t), 0);
+}
+
+static __always_inline void handle(void *ctx)
+{
+	inc_counter();
+	do_stacktrace(ctx);
+}
+
 SEC("?uprobe")
 int bench_trigger_uprobe(void *ctx)
 {
@@ -81,21 +109,21 @@ int trigger_driver_kfunc(void *ctx)
 SEC("?kprobe/bpf_get_numa_node_id")
 int bench_trigger_kprobe(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return 0;
 }
 
 SEC("?kretprobe/bpf_get_numa_node_id")
 int bench_trigger_kretprobe(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return 0;
 }
 
 SEC("?kprobe.multi/bpf_get_numa_node_id")
 int bench_trigger_kprobe_multi(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return 0;
 }
 
@@ -108,7 +136,7 @@ int bench_kprobe_multi_empty(void *ctx)
 SEC("?kretprobe.multi/bpf_get_numa_node_id")
 int bench_trigger_kretprobe_multi(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return 0;
 }
 
@@ -121,34 +149,34 @@ int bench_kretprobe_multi_empty(void *ctx)
 SEC("?fentry/bpf_get_numa_node_id")
 int bench_trigger_fentry(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return 0;
 }
 
 SEC("?fexit/bpf_get_numa_node_id")
 int bench_trigger_fexit(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return 0;
 }
 
 SEC("?fmod_ret/bpf_modify_return_test_tp")
 int bench_trigger_fmodret(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return -22;
 }
 
 SEC("?tp/bpf_test_run/bpf_trigger_tp")
 int bench_trigger_tp(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return 0;
 }
 
 SEC("?raw_tp/bpf_trigger_tp")
 int bench_trigger_rawtp(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_session.c b/tools/testing/selftests/bpf/progs/uprobe_multi_session.c
index 30bff90b68dc..6e46bb00ff58 100644
--- a/tools/testing/selftests/bpf/progs/uprobe_multi_session.c
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi_session.c
@@ -1,9 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/bpf.h>
+#include <vmlinux.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";
@@ -51,7 +50,7 @@ static int uprobe_multi_check(void *ctx, bool is_return)
 SEC("uprobe.session//proc/self/exe:uprobe_multi_func_*")
 int uprobe(struct pt_regs *ctx)
 {
-	return uprobe_multi_check(ctx, bpf_session_is_return());
+	return uprobe_multi_check(ctx, bpf_session_is_return(ctx));
 }
 
 static __always_inline bool verify_sleepable_user_copy(void)
@@ -67,5 +66,5 @@ int uprobe_sleepable(struct pt_regs *ctx)
 {
 	if (verify_sleepable_user_copy())
 		uprobe_multi_sleep_result++;
-	return uprobe_multi_check(ctx, bpf_session_is_return());
+	return uprobe_multi_check(ctx, bpf_session_is_return(ctx));
 }
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_session_cookie.c b/tools/testing/selftests/bpf/progs/uprobe_multi_session_cookie.c
index 5befdf944dc6..b5db196614a9 100644
--- a/tools/testing/selftests/bpf/progs/uprobe_multi_session_cookie.c
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi_session_cookie.c
@@ -1,9 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/bpf.h>
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include <stdbool.h>
-#include "bpf_kfuncs.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -13,16 +12,16 @@ __u64 test_uprobe_1_result = 0;
 __u64 test_uprobe_2_result = 0;
 __u64 test_uprobe_3_result = 0;
 
-static int check_cookie(__u64 val, __u64 *result)
+static int check_cookie(struct pt_regs *ctx, __u64 val, __u64 *result)
 {
 	__u64 *cookie;
 
 	if (bpf_get_current_pid_tgid() >> 32 != pid)
 		return 1;
 
-	cookie = bpf_session_cookie();
+	cookie = bpf_session_cookie(ctx);
 
-	if (bpf_session_is_return())
+	if (bpf_session_is_return(ctx))
 		*result = *cookie == val ? val : 0;
 	else
 		*cookie = val;
@@ -32,17 +31,17 @@ static int check_cookie(__u64 val, __u64 *result)
 SEC("uprobe.session//proc/self/exe:uprobe_multi_func_1")
 int uprobe_1(struct pt_regs *ctx)
 {
-	return check_cookie(1, &test_uprobe_1_result);
+	return check_cookie(ctx, 1, &test_uprobe_1_result);
 }
 
 SEC("uprobe.session//proc/self/exe:uprobe_multi_func_2")
 int uprobe_2(struct pt_regs *ctx)
 {
-	return check_cookie(2, &test_uprobe_2_result);
+	return check_cookie(ctx, 2, &test_uprobe_2_result);
 }
 
 SEC("uprobe.session//proc/self/exe:uprobe_multi_func_3")
 int uprobe_3(struct pt_regs *ctx)
 {
-	return check_cookie(3, &test_uprobe_3_result);
+	return check_cookie(ctx, 3, &test_uprobe_3_result);
 }
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_session_recursive.c b/tools/testing/selftests/bpf/progs/uprobe_multi_session_recursive.c
index 8fbcd69fae22..3ce309248a04 100644
--- a/tools/testing/selftests/bpf/progs/uprobe_multi_session_recursive.c
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi_session_recursive.c
@@ -1,9 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/bpf.h>
+#include <vmlinux.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";
@@ -16,11 +15,11 @@ int idx_return = 0;
 __u64 test_uprobe_cookie_entry[6];
 __u64 test_uprobe_cookie_return[3];
 
-static int check_cookie(void)
+static int check_cookie(struct pt_regs *ctx)
 {
-	__u64 *cookie = bpf_session_cookie();
+	__u64 *cookie = bpf_session_cookie(ctx);
 
-	if (bpf_session_is_return()) {
+	if (bpf_session_is_return(ctx)) {
 		if (idx_return >= ARRAY_SIZE(test_uprobe_cookie_return))
 			return 1;
 		test_uprobe_cookie_return[idx_return++] = *cookie;
@@ -40,5 +39,5 @@ int uprobe_recursive(struct pt_regs *ctx)
 	if (bpf_get_current_pid_tgid() >> 32 != pid)
 		return 1;
 
-	return check_cookie();
+	return check_cookie(ctx);
 }
diff --git a/tools/testing/selftests/bpf/progs/verifier_arena.c b/tools/testing/selftests/bpf/progs/verifier_arena.c
index 7f4827eede3c..c4b8daac4388 100644
--- a/tools/testing/selftests/bpf/progs/verifier_arena.c
+++ b/tools/testing/selftests/bpf/progs/verifier_arena.c
@@ -10,6 +10,8 @@
 #include "bpf_experimental.h"
 #include "bpf_arena_common.h"
 
+#define private(name) SEC(".bss." #name) __hidden __attribute__((aligned(8)))
+
 struct {
 	__uint(type, BPF_MAP_TYPE_ARENA);
 	__uint(map_flags, BPF_F_MMAPABLE);
@@ -21,6 +23,37 @@ struct {
 #endif
 } arena SEC(".maps");
 
+SEC("socket")
+__success __retval(0)
+int basic_alloc1_nosleep(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	volatile int __arena *page1, *page2, *no_page;
+
+	page1 = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (!page1)
+		return 1;
+	*page1 = 1;
+	page2 = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (!page2)
+		return 2;
+	*page2 = 2;
+	no_page = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (no_page)
+		return 3;
+	if (*page1 != 1)
+		return 4;
+	if (*page2 != 2)
+		return 5;
+	bpf_arena_free_pages(&arena, (void __arena *)page2, 1);
+	if (*page1 != 1)
+		return 6;
+	if (*page2 != 0 && *page2 != 2) /* use-after-free should return 0 or the stored value */
+		return 7;
+#endif
+	return 0;
+}
+
 SEC("syscall")
 __success __retval(0)
 int basic_alloc1(void *ctx)
@@ -60,6 +93,44 @@ int basic_alloc1(void *ctx)
 	return 0;
 }
 
+SEC("socket")
+__success __retval(0)
+int basic_alloc2_nosleep(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	volatile char __arena *page1, *page2, *page3, *page4;
+
+	page1 = bpf_arena_alloc_pages(&arena, NULL, 2, NUMA_NO_NODE, 0);
+	if (!page1)
+		return 1;
+	page2 = page1 + __PAGE_SIZE;
+	page3 = page1 + __PAGE_SIZE * 2;
+	page4 = page1 - __PAGE_SIZE;
+	*page1 = 1;
+	*page2 = 2;
+	*page3 = 3;
+	*page4 = 4;
+	if (*page1 != 1)
+		return 1;
+	if (*page2 != 2)
+		return 2;
+	if (*page3 != 0)
+		return 3;
+	if (*page4 != 0)
+		return 4;
+	bpf_arena_free_pages(&arena, (void __arena *)page1, 2);
+	if (*page1 != 0 && *page1 != 1)
+		return 5;
+	if (*page2 != 0 && *page2 != 2)
+		return 6;
+	if (*page3 != 0)
+		return 7;
+	if (*page4 != 0)
+		return 8;
+#endif
+	return 0;
+}
+
 SEC("syscall")
 __success __retval(0)
 int basic_alloc2(void *ctx)
@@ -102,6 +173,19 @@ struct bpf_arena___l {
         struct bpf_map map;
 } __attribute__((preserve_access_index));
 
+SEC("socket")
+__success __retval(0) __log_level(2)
+int basic_alloc3_nosleep(void *ctx)
+{
+	struct bpf_arena___l *ar = (struct bpf_arena___l *)&arena;
+	volatile char __arena *pages;
+
+	pages = bpf_arena_alloc_pages(&ar->map, NULL, ar->map.max_entries, NUMA_NO_NODE, 0);
+	if (!pages)
+		return 1;
+	return 0;
+}
+
 SEC("syscall")
 __success __retval(0) __log_level(2)
 int basic_alloc3(void *ctx)
@@ -115,6 +199,38 @@ int basic_alloc3(void *ctx)
 	return 0;
 }
 
+SEC("socket")
+__success __retval(0)
+int basic_reserve1_nosleep(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	char __arena *page;
+	int ret;
+
+	page = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (!page)
+		return 1;
+
+	page += __PAGE_SIZE;
+
+	/* Reserve the second page */
+	ret = bpf_arena_reserve_pages(&arena, page, 1);
+	if (ret)
+		return 2;
+
+	/* Try to explicitly allocate the reserved page. */
+	page = bpf_arena_alloc_pages(&arena, page, 1, NUMA_NO_NODE, 0);
+	if (page)
+		return 3;
+
+	/* Try to implicitly allocate the page (since there's only 2 of them). */
+	page = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (page)
+		return 4;
+#endif
+	return 0;
+}
+
 SEC("syscall")
 __success __retval(0)
 int basic_reserve1(void *ctx)
@@ -147,6 +263,26 @@ int basic_reserve1(void *ctx)
 	return 0;
 }
 
+SEC("socket")
+__success __retval(0)
+int basic_reserve2_nosleep(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	char __arena *page;
+	int ret;
+
+	page = arena_base(&arena);
+	ret = bpf_arena_reserve_pages(&arena, page, 1);
+	if (ret)
+		return 1;
+
+	page = bpf_arena_alloc_pages(&arena, page, 1, NUMA_NO_NODE, 0);
+	if ((u64)page)
+		return 2;
+#endif
+	return 0;
+}
+
 SEC("syscall")
 __success __retval(0)
 int basic_reserve2(void *ctx)
@@ -168,6 +304,27 @@ int basic_reserve2(void *ctx)
 }
 
 /* Reserve the same page twice, should return -EBUSY. */
+SEC("socket")
+__success __retval(0)
+int reserve_twice_nosleep(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	char __arena *page;
+	int ret;
+
+	page = arena_base(&arena);
+
+	ret = bpf_arena_reserve_pages(&arena, page, 1);
+	if (ret)
+		return 1;
+
+	ret = bpf_arena_reserve_pages(&arena, page, 1);
+	if (ret != -EBUSY)
+		return 2;
+#endif
+	return 0;
+}
+
 SEC("syscall")
 __success __retval(0)
 int reserve_twice(void *ctx)
@@ -190,6 +347,36 @@ int reserve_twice(void *ctx)
 }
 
 /* Try to reserve past the end of the arena. */
+SEC("socket")
+__success __retval(0)
+int reserve_invalid_region_nosleep(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	char __arena *page;
+	int ret;
+
+	/* Try a NULL pointer. */
+	ret = bpf_arena_reserve_pages(&arena, NULL, 3);
+	if (ret != -EINVAL)
+		return 1;
+
+	page = arena_base(&arena);
+
+	ret = bpf_arena_reserve_pages(&arena, page, 3);
+	if (ret != -EINVAL)
+		return 2;
+
+	ret = bpf_arena_reserve_pages(&arena, page, 4096);
+	if (ret != -EINVAL)
+		return 3;
+
+	ret = bpf_arena_reserve_pages(&arena, page, (1ULL << 32) - 1);
+	if (ret != -EINVAL)
+		return 4;
+#endif
+	return 0;
+}
+
 SEC("syscall")
 __success __retval(0)
 int reserve_invalid_region(void *ctx)
@@ -254,4 +441,40 @@ int iter_maps3(struct bpf_iter__bpf_map *ctx)
 	return 0;
 }
 
+private(ARENA_TESTS) struct bpf_spin_lock arena_bpf_test_lock;
+
+/* Use the arena kfunc API while under a BPF lock. */
+SEC("syscall")
+__success __retval(0)
+int arena_kfuncs_under_bpf_lock(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	char __arena *page;
+	int ret;
+
+	bpf_spin_lock(&arena_bpf_test_lock);
+
+	/* Get a separate region of the arena. */
+	page = arena_base(&arena);
+	ret = bpf_arena_reserve_pages(&arena, page, 1);
+	if (ret) {
+		bpf_spin_unlock(&arena_bpf_test_lock);
+		return 1;
+	}
+
+	bpf_arena_free_pages(&arena, page, 1);
+
+	page = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (!page) {
+		bpf_spin_unlock(&arena_bpf_test_lock);
+		return 2;
+	}
+
+	bpf_arena_free_pages(&arena, page, 1);
+
+	bpf_spin_unlock(&arena_bpf_test_lock);
+#endif
+
+	return 0;
+}
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_arena_globals1.c b/tools/testing/selftests/bpf/progs/verifier_arena_globals1.c
new file mode 100644
index 000000000000..83182ddbfb95
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_arena_globals1.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#define BPF_NO_KFUNC_PROTOTYPES
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_experimental.h"
+#include "bpf_arena_common.h"
+#include "bpf_misc.h"
+
+#define ARENA_PAGES (1UL<< (32 - __builtin_ffs(__PAGE_SIZE) + 1))
+#define GLOBAL_PAGES (16)
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, ARENA_PAGES);
+#ifdef __TARGET_ARCH_arm64
+	__ulong(map_extra, (1ull << 32) | (~0u - __PAGE_SIZE * ARENA_PAGES + 1));
+#else
+	__ulong(map_extra, (1ull << 44) | (~0u - __PAGE_SIZE * ARENA_PAGES + 1));
+#endif
+} arena SEC(".maps");
+
+/*
+ * Global data, to be placed at the end of the arena.
+ */
+volatile char __arena global_data[GLOBAL_PAGES][PAGE_SIZE];
+
+SEC("syscall")
+__success __retval(0)
+int check_reserve1(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	const u8 magic = 0x5a;
+	__u8 __arena *guard, *globals;
+	volatile char __arena *ptr;
+	int i;
+	int ret;
+
+	guard = (void __arena *)arena_base(&arena);
+	globals = (void __arena *)(arena_base(&arena) + (ARENA_PAGES - GLOBAL_PAGES) * PAGE_SIZE);
+
+	/* Reserve the region we've offset the globals by. */
+	ret = bpf_arena_reserve_pages(&arena, guard, ARENA_PAGES - GLOBAL_PAGES);
+	if (ret)
+		return 1;
+
+	/* Make sure the globals are in the expected offset. */
+	ret = bpf_arena_reserve_pages(&arena, globals, 1);
+	if (!ret)
+		return 2;
+
+	/* Verify globals are properly mapped in by libbpf. */
+	for (i = 0; i < GLOBAL_PAGES; i++) {
+		ptr = &global_data[i][PAGE_SIZE / 2];
+
+		*ptr = magic;
+		if (*ptr != magic)
+			return i + 3;
+	}
+#endif
+	return 0;
+}
+
+/*
+ * Relocation check by reading directly into the global data w/o using symbols.
+ */
+SEC("syscall")
+__success __retval(0)
+int check_relocation(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	const u8 magic = 0xfa;
+	u8 __arena *ptr;
+
+	global_data[GLOBAL_PAGES - 1][PAGE_SIZE / 2] = magic;
+	ptr = (u8 __arena *)((u64)(ARENA_PAGES * PAGE_SIZE - PAGE_SIZE / 2));
+	if (*ptr != magic)
+		return 1;
+
+#endif
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_arena_globals2.c b/tools/testing/selftests/bpf/progs/verifier_arena_globals2.c
new file mode 100644
index 000000000000..e6bd7b61f9f1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_arena_globals2.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#define BPF_NO_KFUNC_PROTOTYPES
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+#include "bpf_arena_common.h"
+
+#define ARENA_PAGES (32)
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, ARENA_PAGES);
+#ifdef __TARGET_ARCH_arm64
+	__ulong(map_extra, (1ull << 32) | (~0u - __PAGE_SIZE * ARENA_PAGES + 1));
+#else
+	__ulong(map_extra, (1ull << 44) | (~0u - __PAGE_SIZE * ARENA_PAGES + 1));
+#endif
+} arena SEC(".maps");
+
+/*
+ * Fill the entire arena with global data.
+ * The offset into the arena should be 0.
+ */
+char __arena global_data[ARENA_PAGES][PAGE_SIZE];
+
+SEC("syscall")
+__success __retval(0)
+int check_reserve2(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	void __arena *guard;
+	int ret;
+
+	guard = (void __arena *)arena_base(&arena);
+
+	/* Make sure the data at offset 0 case is properly handled. */
+	ret = bpf_arena_reserve_pages(&arena, guard, 1);
+	if (!ret)
+		return 1;
+#endif
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_arena_large.c b/tools/testing/selftests/bpf/progs/verifier_arena_large.c
index f19e15400b3e..5f7e7afee169 100644
--- a/tools/testing/selftests/bpf/progs/verifier_arena_large.c
+++ b/tools/testing/selftests/bpf/progs/verifier_arena_large.c
@@ -23,18 +23,31 @@ int big_alloc1(void *ctx)
 {
 #if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
 	volatile char __arena *page1, *page2, *no_page, *page3;
-	void __arena *base;
+	u64 base;
 
-	page1 = base = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	base = (u64)arena_base(&arena);
+
+	page1 = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
 	if (!page1)
 		return 1;
+
+	if ((u64)page1 != base)
+		return 15;
+
 	*page1 = 1;
-	page2 = bpf_arena_alloc_pages(&arena, base + ARENA_SIZE - PAGE_SIZE * 2,
+	page2 = bpf_arena_alloc_pages(&arena, (void __arena *)(ARENA_SIZE - 2 * PAGE_SIZE),
 				      1, NUMA_NO_NODE, 0);
 	if (!page2)
 		return 2;
 	*page2 = 2;
-	no_page = bpf_arena_alloc_pages(&arena, base + ARENA_SIZE - PAGE_SIZE,
+
+	/* Test for the guard region at the end of the arena. */
+	no_page = bpf_arena_alloc_pages(&arena, (void __arena *)ARENA_SIZE - PAGE_SIZE,
+					1, NUMA_NO_NODE, 0);
+	if (no_page)
+		return 16;
+
+	no_page = bpf_arena_alloc_pages(&arena, (void __arena *)ARENA_SIZE,
 					1, NUMA_NO_NODE, 0);
 	if (no_page)
 		return 3;
@@ -270,5 +283,34 @@ int big_alloc2(void *ctx)
 		return 9;
 	return 0;
 }
+
+SEC("socket")
+__success __retval(0)
+int big_alloc3(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	char __arena *pages;
+	u64 i;
+
+	/*
+	 * Allocate 2051 pages in one go to check how kmalloc_nolock() handles large requests.
+	 * Since kmalloc_nolock() can allocate up to 1024 struct page * at a time, this call should
+	 * result in three batches: two batches of 1024 pages each, followed by a final batch of 3
+	 * pages.
+	 */
+	pages = bpf_arena_alloc_pages(&arena, NULL, 2051, NUMA_NO_NODE, 0);
+	if (!pages)
+		return 0;
+
+	bpf_for(i, 0, 2051)
+			pages[i * PAGE_SIZE] = 123;
+	bpf_for(i, 0, 2051)
+			if (pages[i * PAGE_SIZE] != 123)
+				return i;
+
+	bpf_arena_free_pages(&arena, pages, 2051);
+#endif
+	return 0;
+}
 #endif
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c b/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c
index 7efa9521105e..39aff82549c9 100644
--- a/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c
+++ b/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c
@@ -96,7 +96,7 @@ int wq_non_sleepable_prog(void *ctx)
 
 	if (bpf_wq_init(&val->w, &wq_map, 0) != 0)
 		return 0;
-	if (bpf_wq_set_callback_impl(&val->w, wq_cb, 0, NULL) != 0)
+	if (bpf_wq_set_callback(&val->w, wq_cb, 0) != 0)
 		return 0;
 	return 0;
 }
@@ -114,7 +114,7 @@ int wq_sleepable_prog(void *ctx)
 
 	if (bpf_wq_init(&val->w, &wq_map, 0) != 0)
 		return 0;
-	if (bpf_wq_set_callback_impl(&val->w, wq_cb, 0, NULL) != 0)
+	if (bpf_wq_set_callback(&val->w, wq_cb, 0) != 0)
 		return 0;
 	return 0;
 }
@@ -156,7 +156,7 @@ int task_work_non_sleepable_prog(void *ctx)
 	if (!task)
 		return 0;
 
-	bpf_task_work_schedule_resume_impl(task, &val->tw, &task_work_map, task_work_cb, NULL);
+	bpf_task_work_schedule_resume(task, &val->tw, &task_work_map, task_work_cb);
 	return 0;
 }
 
@@ -176,6 +176,6 @@ int task_work_sleepable_prog(void *ctx)
 	if (!task)
 		return 0;
 
-	bpf_task_work_schedule_resume_impl(task, &val->tw, &task_work_map, task_work_cb, NULL);
+	bpf_task_work_schedule_resume(task, &val->tw, &task_work_map, task_work_cb);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c
index 411a18437d7e..560531404bce 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bounds.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c
@@ -1477,7 +1477,7 @@ __naked void sub64_full_overflow(void)
 SEC("socket")
 __description("64-bit subtraction, partial overflow, result in unbounded reg")
 __success __log_level(2)
-__msg("3: (1f) r3 -= r2 {{.*}} R3=scalar()")
+__msg("3: (1f) r3 -= r2 {{.*}} R3=scalar(id=1-1)")
 __retval(0)
 __naked void sub64_partial_overflow(void)
 {
diff --git a/tools/testing/selftests/bpf/progs/verifier_bswap.c b/tools/testing/selftests/bpf/progs/verifier_bswap.c
index e61755656e8d..4b779deee767 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bswap.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bswap.c
@@ -48,6 +48,49 @@ __naked void bswap_64(void)
 	: __clobber_all);
 }
 
+#define BSWAP_RANGE_TEST(name, op, in_value, out_value) \
+	SEC("socket") \
+	__success __log_level(2) \
+	__msg("r0 &= {{.*}}; R0=scalar({{.*}},var_off=(0x0; " #in_value "))") \
+	__msg("r0 = " op " r0 {{.*}}; R0=scalar({{.*}},var_off=(0x0; " #out_value "))") \
+	__naked void name(void) \
+	{ \
+		asm volatile (				\
+		"call %[bpf_get_prandom_u32];"		\
+		"r0 &= " #in_value ";"			\
+		"r0 =  " op " r0;"			\
+		"r2 =  " #out_value " ll;"		\
+		"if r0 > r2 goto trap_%=;"		\
+		"r0 = 0;"				\
+		"exit;"					\
+	"trap_%=:"					\
+		"r1 = 42;"				\
+		"r0 = *(u64 *)(r1 + 0);"		\
+		"exit;"					\
+	:						\
+	: __imm(bpf_get_prandom_u32)			\
+	: __clobber_all);				\
+	}
+
+BSWAP_RANGE_TEST(bswap16_range, "bswap16", 0x3f00, 0x3f)
+BSWAP_RANGE_TEST(bswap32_range, "bswap32", 0x3f00, 0x3f0000)
+BSWAP_RANGE_TEST(bswap64_range, "bswap64", 0x3f00, 0x3f000000000000)
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+BSWAP_RANGE_TEST(be16_range, "be16", 0x3f00, 0x3f)
+BSWAP_RANGE_TEST(be32_range, "be32", 0x3f00, 0x3f0000)
+BSWAP_RANGE_TEST(be64_range, "be64", 0x3f00, 0x3f000000000000)
+BSWAP_RANGE_TEST(le16_range, "le16", 0x3f00, 0x3f00)
+BSWAP_RANGE_TEST(le32_range, "le32", 0x3f00, 0x3f00)
+BSWAP_RANGE_TEST(le64_range, "le64", 0x3f00, 0x3f00)
+#else
+BSWAP_RANGE_TEST(be16_range, "be16", 0x3f00, 0x3f00)
+BSWAP_RANGE_TEST(be32_range, "be32", 0x3f00, 0x3f00)
+BSWAP_RANGE_TEST(be64_range, "be64", 0x3f00, 0x3f00)
+BSWAP_RANGE_TEST(le16_range, "le16", 0x3f00, 0x3f)
+BSWAP_RANGE_TEST(le32_range, "le32", 0x3f00, 0x3f0000)
+BSWAP_RANGE_TEST(le64_range, "le64", 0x3f00, 0x3f000000000000)
+#endif
+
 #else
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_default_trusted_ptr.c b/tools/testing/selftests/bpf/progs/verifier_default_trusted_ptr.c
new file mode 100644
index 000000000000..fa3b656ad4fb
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_default_trusted_ptr.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2026 Google LLC.
+ */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+SEC("syscall")
+__success __retval(0)
+int test_default_trusted_ptr(void *ctx)
+{
+	struct prog_test_member *trusted_ptr;
+
+	trusted_ptr = bpf_kfunc_get_default_trusted_ptr_test();
+	/*
+	 * Test BPF kfunc bpf_get_default_trusted_ptr_test() returns a
+	 * PTR_TO_BTF_ID | PTR_TRUSTED, therefore it should be accepted when
+	 * passed to a BPF kfunc only accepting KF_TRUSTED_ARGS.
+	 */
+	bpf_kfunc_put_default_trusted_ptr_test(trusted_ptr);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_div_mod_bounds.c b/tools/testing/selftests/bpf/progs/verifier_div_mod_bounds.c
new file mode 100644
index 000000000000..4672af0b3268
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_div_mod_bounds.c
@@ -0,0 +1,1149 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <limits.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+/* This file contains unit tests for signed/unsigned division and modulo
+ * operations (with divisor as a constant), focusing on verifying whether
+ * BPF verifier's range tracking module soundly and precisely computes
+ * the results.
+ */
+
+SEC("socket")
+__description("UDIV32, positive divisor")
+__success __retval(0) __log_level(2)
+__msg("w1 /= 3 {{.*}}; R1=scalar(smin=smin32=0,smax=umax=smax32=umax32=3,var_off=(0x0; 0x3))")
+__naked void udiv32_pos_divisor(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	w1 &= 8;					\
+	w1 |= 1;					\
+	w1 /= 3;					\
+	if w1 > 3 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("UDIV32, zero divisor")
+__success __retval(0) __log_level(2)
+__msg("w1 /= w2 {{.*}}; R1=0 R2=0")
+__naked void udiv32_zero_divisor(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	w1 &= 8;					\
+	w1 |= 1;					\
+	w2 = 0;						\
+	w1 /= w2;					\
+	if w1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("UDIV64, positive divisor")
+__success __retval(0) __log_level(2)
+__msg("r1 /= 3 {{.*}}; R1=scalar(smin=smin32=0,smax=umax=smax32=umax32=3,var_off=(0x0; 0x3))")
+__naked void udiv64_pos_divisor(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	r1 &= 8;					\
+	r1 |= 1;					\
+	r1 /= 3;					\
+	if r1 > 3 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("UDIV64, zero divisor")
+__success __retval(0) __log_level(2)
+__msg("r1 /= r2 {{.*}}; R1=0 R2=0")
+__naked void udiv64_zero_divisor(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	r1 &= 8;					\
+	r1 |= 1;					\
+	r2 = 0;						\
+	r1 /= r2;					\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, positive divisor, positive dividend")
+__success __retval(0) __log_level(2)
+__msg("w1 s/= 3 {{.*}}; R1=scalar(smin=umin=smin32=umin32=2,smax=umax=smax32=umax32=3,var_off=(0x2; 0x1))")
+__naked void sdiv32_pos_divisor_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	if w1 s< 8 goto l0_%=;				\
+	if w1 s> 10 goto l0_%=;				\
+	w1 s/= 3;					\
+	if w1 s< 2 goto l1_%=;				\
+	if w1 s> 3 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, positive divisor, negative dividend")
+__success __retval(0) __log_level(2)
+__msg("w1 s/= 3 {{.*}}; R1=scalar(smin=umin=umin32=0xfffffffd,smax=umax=umax32=0xfffffffe,smin32=-3,smax32=-2,var_off=(0xfffffffc; 0x3))")
+__naked void sdiv32_pos_divisor_2(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	if w1 s> -8 goto l0_%=;				\
+	if w1 s< -10 goto l0_%=;			\
+	w1 s/= 3;					\
+	if w1 s< -3 goto l1_%=;				\
+	if w1 s> -2 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, positive divisor, mixed sign dividend")
+__success __retval(0) __log_level(2)
+__msg("w1 s/= 3 {{.*}}; R1=scalar(smin=0,smax=umax=0xffffffff,smin32=-2,smax32=3,var_off=(0x0; 0xffffffff))")
+__naked void sdiv32_pos_divisor_3(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	if w1 s< -8 goto l0_%=;				\
+	if w1 s> 10 goto l0_%=;				\
+	w1 s/= 3;					\
+	if w1 s< -2 goto l1_%=;				\
+	if w1 s> 3 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, negative divisor, positive dividend")
+__success __retval(0) __log_level(2)
+__msg("w1 s/= -3 {{.*}}; R1=scalar(smin=umin=umin32=0xfffffffd,smax=umax=umax32=0xfffffffe,smin32=-3,smax32=-2,var_off=(0xfffffffc; 0x3))")
+__naked void sdiv32_neg_divisor_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	if w1 s< 8 goto l0_%=;				\
+	if w1 s> 10 goto l0_%=;				\
+	w1 s/= -3;					\
+	if w1 s< -3 goto l1_%=;				\
+	if w1 s> -2 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, negative divisor, positive dividend")
+__success __retval(0) __log_level(2)
+__msg("w1 s/= -3 {{.*}}; R1=scalar(smin=umin=smin32=umin32=2,smax=umax=smax32=umax32=3,var_off=(0x2; 0x1))")
+__naked void sdiv32_neg_divisor_2(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	if w1 s> -8 goto l0_%=;				\
+	if w1 s< -10 goto l0_%=;			\
+	w1 s/= -3;					\
+	if w1 s< 2 goto l1_%=;				\
+	if w1 s> 3 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, negative divisor, mixed sign dividend")
+__success __retval(0) __log_level(2)
+__msg("w1 s/= -3 {{.*}}; R1=scalar(smin=0,smax=umax=0xffffffff,smin32=-3,smax32=2,var_off=(0x0; 0xffffffff))")
+__naked void sdiv32_neg_divisor_3(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	if w1 s< -8 goto l0_%=;				\
+	if w1 s> 10 goto l0_%=;				\
+	w1 s/= -3;					\
+	if w1 s< -3 goto l1_%=;				\
+	if w1 s> 2 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, zero divisor")
+__success __retval(0) __log_level(2)
+__msg("w1 s/= w2 {{.*}}; R1=0 R2=0")
+__naked void sdiv32_zero_divisor(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	w1 &= 8;					\
+	w1 |= 1;					\
+	w2 = 0;						\
+	w1 s/= w2;					\
+	if w1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, overflow (S32_MIN/-1)")
+__success __retval(0) __log_level(2)
+__msg("w1 s/= -1 {{.*}}; R1=scalar(smin=0,smax=umax=0xffffffff,var_off=(0x0; 0xffffffff))")
+__naked void sdiv32_overflow_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	w2 = %[int_min];				\
+	w2 += 10;					\
+	if w1 s> w2 goto l0_%=;				\
+	w1 s/= -1;					\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN),
+	  __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, overflow (S32_MIN/-1), constant dividend")
+__success __retval(0) __log_level(2)
+__msg("w1 s/= -1 {{.*}}; R1=0x80000000")
+__naked void sdiv32_overflow_2(void)
+{
+	asm volatile ("					\
+	w1 = %[int_min];				\
+	w1 s/= -1;					\
+	if w1 != %[int_min] goto l0_%=;			\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, positive divisor, positive dividend")
+__success __retval(0) __log_level(2)
+__msg("r1 s/= 3 {{.*}}; R1=scalar(smin=umin=smin32=umin32=2,smax=umax=smax32=umax32=3,var_off=(0x2; 0x1))")
+__naked void sdiv64_pos_divisor_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	if r1 s< 8 goto l0_%=;				\
+	if r1 s> 10 goto l0_%=;				\
+	r1 s/= 3;					\
+	if r1 s< 2 goto l1_%=;				\
+	if r1 s> 3 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, positive divisor, negative dividend")
+__success __retval(0) __log_level(2)
+__msg("r1 s/= 3 {{.*}}; R1=scalar(smin=smin32=-3,smax=smax32=-2,umin=0xfffffffffffffffd,umax=0xfffffffffffffffe,umin32=0xfffffffd,umax32=0xfffffffe,var_off=(0xfffffffffffffffc; 0x3))")
+__naked void sdiv64_pos_divisor_2(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	if r1 s> -8 goto l0_%=;				\
+	if r1 s< -10 goto l0_%=;			\
+	r1 s/= 3;					\
+	if r1 s< -3 goto l1_%=;				\
+	if r1 s> -2 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, positive divisor, mixed sign dividend")
+__success __retval(0) __log_level(2)
+__msg("r1 s/= 3 {{.*}}; R1=scalar(smin=smin32=-2,smax=smax32=3)")
+__naked void sdiv64_pos_divisor_3(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	if r1 s< -8 goto l0_%=;				\
+	if r1 s> 10 goto l0_%=;				\
+	r1 s/= 3;					\
+	if r1 s< -2 goto l1_%=;				\
+	if r1 s> 3 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, negative divisor, positive dividend")
+__success __retval(0) __log_level(2)
+__msg("r1 s/= -3 {{.*}}; R1=scalar(smin=smin32=-3,smax=smax32=-2,umin=0xfffffffffffffffd,umax=0xfffffffffffffffe,umin32=0xfffffffd,umax32=0xfffffffe,var_off=(0xfffffffffffffffc; 0x3))")
+__naked void sdiv64_neg_divisor_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	if r1 s< 8 goto l0_%=;				\
+	if r1 s> 10 goto l0_%=;				\
+	r1 s/= -3;					\
+	if r1 s< -3 goto l1_%=;				\
+	if r1 s> -2 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, negative divisor, positive dividend")
+__success __retval(0) __log_level(2)
+__msg("r1 s/= -3 {{.*}}; R1=scalar(smin=umin=smin32=umin32=2,smax=umax=smax32=umax32=3,var_off=(0x2; 0x1))")
+__naked void sdiv64_neg_divisor_2(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	if r1 s> -8 goto l0_%=;				\
+	if r1 s< -10 goto l0_%=;			\
+	r1 s/= -3;					\
+	if r1 s< 2 goto l1_%=;				\
+	if r1 s> 3 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, negative divisor, mixed sign dividend")
+__success __retval(0) __log_level(2)
+__msg("r1 s/= -3 {{.*}}; R1=scalar(smin=smin32=-3,smax=smax32=2)")
+__naked void sdiv64_neg_divisor_3(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	if r1 s< -8 goto l0_%=;				\
+	if r1 s> 10 goto l0_%=;				\
+	r1 s/= -3;					\
+	if r1 s< -3 goto l1_%=;				\
+	if r1 s> 2 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, zero divisor")
+__success __retval(0) __log_level(2)
+__msg("r1 s/= r2 {{.*}}; R1=0 R2=0")
+__naked void sdiv64_zero_divisor(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	r1 &= 8;					\
+	r1 |= 1;					\
+	r2 = 0;						\
+	r1 s/= r2;					\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, overflow (S64_MIN/-1)")
+__success __retval(0) __log_level(2)
+__msg("r1 s/= -1 {{.*}}; R1=scalar()")
+__naked void sdiv64_overflow_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	r1 = r0;					\
+	r2 = %[llong_min] ll;				\
+	r2 += 10;					\
+	if r1 s> r2 goto l0_%=;				\
+	r1 s/= -1;					\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(llong_min, LLONG_MIN),
+	  __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, overflow (S64_MIN/-1), constant dividend")
+__success __retval(0) __log_level(2)
+__msg("r1 s/= -1 {{.*}}; R1=0x8000000000000000")
+__naked void sdiv64_overflow_2(void)
+{
+	asm volatile ("					\
+	r1 = %[llong_min] ll;				\
+	r1 s/= -1;					\
+	r2 = %[llong_min] ll;				\
+	if r1 != r2 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm_const(llong_min, LLONG_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("UMOD32, positive divisor")
+__success __retval(0) __log_level(2)
+__msg("w1 %= 3 {{.*}}; R1=scalar(smin=smin32=0,smax=umax=smax32=umax32=2,var_off=(0x0; 0x3))")
+__naked void umod32_pos_divisor(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	w1 &= 8;					\
+	w1 |= 1;					\
+	w1 %%= 3;					\
+	if w1 > 3 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("UMOD32, positive divisor, small dividend")
+__success __retval(0) __log_level(2)
+__msg("w1 %= 10 {{.*}}; R1=scalar(smin=umin=smin32=umin32=1,smax=umax=smax32=umax32=9,var_off=(0x1; 0x8))")
+__naked void umod32_pos_divisor_unchanged(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	w1 &= 8;					\
+	w1 |= 1;					\
+	w1 %%= 10;					\
+	if w1 < 1 goto l0_%=;				\
+	if w1 > 9 goto l0_%=;				\
+	if w1 & 1 != 1 goto l0_%=;			\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("UMOD32, zero divisor")
+__success __retval(0) __log_level(2)
+__msg("w1 %= w2 {{.*}}; R1=scalar(smin=umin=smin32=umin32=1,smax=umax=smax32=umax32=9,var_off=(0x1; 0x8)) R2=0")
+__naked void umod32_zero_divisor(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	w1 &= 8;					\
+	w1 |= 1;					\
+	w2 = 0;						\
+	w1 %%= w2;					\
+	if w1 < 1 goto l0_%=;				\
+	if w1 > 9 goto l0_%=;				\
+	if w1 & 1 != 1 goto l0_%=;			\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("UMOD64, positive divisor")
+__success __retval(0) __log_level(2)
+__msg("r1 %= 3 {{.*}}; R1=scalar(smin=smin32=0,smax=umax=smax32=umax32=2,var_off=(0x0; 0x3))")
+__naked void umod64_pos_divisor(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	r1 &= 8;					\
+	r1 |= 1;					\
+	r1 %%= 3;					\
+	if r1 > 3 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("UMOD64, positive divisor, small dividend")
+__success __retval(0) __log_level(2)
+__msg("r1 %= 10 {{.*}}; R1=scalar(smin=umin=smin32=umin32=1,smax=umax=smax32=umax32=9,var_off=(0x1; 0x8))")
+__naked void umod64_pos_divisor_unchanged(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	r1 &= 8;					\
+	r1 |= 1;					\
+	r1 %%= 10;					\
+	if r1 < 1 goto l0_%=;				\
+	if r1 > 9 goto l0_%=;				\
+	if r1 & 1 != 1 goto l0_%=;			\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("UMOD64, zero divisor")
+__success __retval(0) __log_level(2)
+__msg("r1 %= r2 {{.*}}; R1=scalar(smin=umin=smin32=umin32=1,smax=umax=smax32=umax32=9,var_off=(0x1; 0x8)) R2=0")
+__naked void umod64_zero_divisor(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	r1 &= 8;					\
+	r1 |= 1;					\
+	r2 = 0;						\
+	r1 %%= r2;					\
+	if r1 < 1 goto l0_%=;				\
+	if r1 > 9 goto l0_%=;				\
+	if r1 & 1 != 1 goto l0_%=;			\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, positive divisor, positive dividend")
+__success __retval(0) __log_level(2)
+__msg("w1 s%= 3 {{.*}}; R1=scalar(smin=smin32=0,smax=umax=smax32=umax32=2,var_off=(0x0; 0x3))")
+__naked void smod32_pos_divisor_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	if w1 s< 8 goto l0_%=;				\
+	if w1 s> 10 goto l0_%=;				\
+	w1 s%%= 3;					\
+	if w1 s< 0 goto l1_%=;				\
+	if w1 s> 2 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, positive divisor, negative dividend")
+__success __retval(0) __log_level(2)
+__msg("w1 s%= 3 {{.*}}; R1=scalar(smin=0,smax=umax=0xffffffff,smin32=-2,smax32=0,var_off=(0x0; 0xffffffff))")
+__naked void smod32_pos_divisor_2(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	if w1 s> -8 goto l0_%=;				\
+	if w1 s< -10 goto l0_%=;			\
+	w1 s%%= 3;					\
+	if w1 s< -2 goto l1_%=;				\
+	if w1 s> 0 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, positive divisor, mixed sign dividend")
+__success __retval(0) __log_level(2)
+__msg("w1 s%= 3 {{.*}}; R1=scalar(smin=0,smax=umax=0xffffffff,smin32=-2,smax32=2,var_off=(0x0; 0xffffffff))")
+__naked void smod32_pos_divisor_3(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	if w1 s< -8 goto l0_%=;				\
+	if w1 s> 10 goto l0_%=;				\
+	w1 s%%= 3;					\
+	if w1 s< -2 goto l1_%=;				\
+	if w1 s> 2 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, positive divisor, small dividend")
+__success __retval(0) __log_level(2)
+__msg("w1 s%= 11 {{.*}}; R1=scalar(smin=0,smax=umax=0xffffffff,smin32=-8,smax32=10,var_off=(0x0; 0xffffffff))")
+__naked void smod32_pos_divisor_unchanged(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	if w1 s< -8 goto l0_%=;				\
+	if w1 s> 10 goto l0_%=;				\
+	w1 s%%= 11;					\
+	if w1 s< -8 goto l1_%=;				\
+	if w1 s> 10 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, negative divisor, positive dividend")
+__success __retval(0) __log_level(2)
+__msg("w1 s%= -3 {{.*}}; R1=scalar(smin=smin32=0,smax=umax=smax32=umax32=2,var_off=(0x0; 0x3))")
+__naked void smod32_neg_divisor_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	if w1 s< 8 goto l0_%=;				\
+	if w1 s> 10 goto l0_%=;				\
+	w1 s%%= -3;					\
+	if w1 s< 0 goto l1_%=;				\
+	if w1 s> 2 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, negative divisor, negative dividend")
+__success __retval(0) __log_level(2)
+__msg("w1 s%= -3 {{.*}}; R1=scalar(smin=0,smax=umax=0xffffffff,smin32=-2,smax32=0,var_off=(0x0; 0xffffffff))")
+__naked void smod32_neg_divisor_2(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	if w1 s> -8 goto l0_%=;				\
+	if w1 s< -10 goto l0_%=;			\
+	w1 s%%= -3;					\
+	if w1 s< -2 goto l1_%=;				\
+	if w1 s> 0 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, negative divisor, mixed sign dividend")
+__success __retval(0) __log_level(2)
+__msg("w1 s%= -3 {{.*}}; R1=scalar(smin=0,smax=umax=0xffffffff,smin32=-2,smax32=2,var_off=(0x0; 0xffffffff))")
+__naked void smod32_neg_divisor_3(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	if w1 s< -8 goto l0_%=;				\
+	if w1 s> 10 goto l0_%=;				\
+	w1 s%%= -3;					\
+	if w1 s< -2 goto l1_%=;				\
+	if w1 s> 2 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, negative divisor, small dividend")
+__success __retval(0) __log_level(2)
+__msg("w1 s%= -11 {{.*}}; R1=scalar(smin=0,smax=umax=0xffffffff,smin32=-8,smax32=10,var_off=(0x0; 0xffffffff))")
+__naked void smod32_neg_divisor_unchanged(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	if w1 s< -8 goto l0_%=;				\
+	if w1 s> 10 goto l0_%=;				\
+	w1 s%%= -11;					\
+	if w1 s< -8 goto l1_%=;				\
+	if w1 s> 10 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, zero divisor")
+__success __retval(0) __log_level(2)
+__msg("w1 s%= w2 {{.*}}; R1=scalar(smin=0,smax=umax=0xffffffff,smin32=-8,smax32=10,var_off=(0x0; 0xffffffff)) R2=0")
+__naked void smod32_zero_divisor(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	if w1 s< -8 goto l0_%=;				\
+	if w1 s> 10 goto l0_%=;				\
+	w2 = 0;						\
+	w1 s%%= w2;					\
+	if w1 s< -8 goto l1_%=;				\
+	if w1 s> 10 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, overflow (S32_MIN%-1)")
+__success __retval(0) __log_level(2)
+__msg("w1 s%= -1 {{.*}}; R1=0")
+__naked void smod32_overflow_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = w0;					\
+	w2 = %[int_min];				\
+	w2 += 10;					\
+	if w1 s> w2 goto l0_%=;				\
+	w1 s%%= -1;					\
+	if w1 != 0 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN),
+	  __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, overflow (S32_MIN%-1), constant dividend")
+__success __retval(0) __log_level(2)
+__msg("w1 s%= -1 {{.*}}; R1=0")
+__naked void smod32_overflow_2(void)
+{
+	asm volatile ("					\
+	w1 = %[int_min];				\
+	w1 s%%= -1;					\
+	if w1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, positive divisor, positive dividend")
+__success __retval(0) __log_level(2)
+__msg("r1 s%= 3 {{.*}}; R1=scalar(smin=smin32=0,smax=umax=smax32=umax32=2,var_off=(0x0; 0x3))")
+__naked void smod64_pos_divisor_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	if r1 s< 8 goto l0_%=;				\
+	if r1 s> 10 goto l0_%=;				\
+	r1 s%%= 3;					\
+	if r1 s< 0 goto l1_%=;				\
+	if r1 s> 2 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, positive divisor, negative dividend")
+__success __retval(0) __log_level(2)
+__msg("r1 s%= 3 {{.*}}; R1=scalar(smin=smin32=-2,smax=smax32=0)")
+__naked void smod64_pos_divisor_2(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	if r1 s> -8 goto l0_%=;				\
+	if r1 s< -10 goto l0_%=;			\
+	r1 s%%= 3;					\
+	if r1 s< -2 goto l1_%=;				\
+	if r1 s> 0 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, positive divisor, mixed sign dividend")
+__success __retval(0) __log_level(2)
+__msg("r1 s%= 3 {{.*}}; R1=scalar(smin=smin32=-2,smax=smax32=2)")
+__naked void smod64_pos_divisor_3(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	if r1 s< -8 goto l0_%=;				\
+	if r1 s> 10 goto l0_%=;				\
+	r1 s%%= 3;					\
+	if r1 s< -2 goto l1_%=;				\
+	if r1 s> 2 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, positive divisor, small dividend")
+__success __retval(0) __log_level(2)
+__msg("r1 s%= 11 {{.*}}; R1=scalar(smin=smin32=-8,smax=smax32=10)")
+__naked void smod64_pos_divisor_unchanged(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	if r1 s< -8 goto l0_%=;				\
+	if r1 s> 10 goto l0_%=;				\
+	r1 s%%= 11;					\
+	if r1 s< -8 goto l1_%=;				\
+	if r1 s> 10 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, negative divisor, positive dividend")
+__success __retval(0) __log_level(2)
+__msg("r1 s%= -3 {{.*}}; R1=scalar(smin=smin32=0,smax=umax=smax32=umax32=2,var_off=(0x0; 0x3))")
+__naked void smod64_neg_divisor_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	if r1 s< 8 goto l0_%=;				\
+	if r1 s> 10 goto l0_%=;				\
+	r1 s%%= -3;					\
+	if r1 s< 0 goto l1_%=;				\
+	if r1 s> 2 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, negative divisor, negative dividend")
+__success __retval(0) __log_level(2)
+__msg("r1 s%= -3 {{.*}}; R1=scalar(smin=smin32=-2,smax=smax32=0)")
+__naked void smod64_neg_divisor_2(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	if r1 s> -8 goto l0_%=;				\
+	if r1 s< -10 goto l0_%=;			\
+	r1 s%%= -3;					\
+	if r1 s< -2 goto l1_%=;				\
+	if r1 s> 0 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, negative divisor, mixed sign dividend")
+__success __retval(0) __log_level(2)
+__msg("r1 s%= -3 {{.*}}; R1=scalar(smin=smin32=-2,smax=smax32=2)")
+__naked void smod64_neg_divisor_3(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	if r1 s< -8 goto l0_%=;				\
+	if r1 s> 10 goto l0_%=;				\
+	r1 s%%= -3;					\
+	if r1 s< -2 goto l1_%=;				\
+	if r1 s> 2 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, negative divisor, small dividend")
+__success __retval(0) __log_level(2)
+__msg("r1 s%= -11 {{.*}}; R1=scalar(smin=smin32=-8,smax=smax32=10)")
+__naked void smod64_neg_divisor_unchanged(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	if r1 s< -8 goto l0_%=;				\
+	if r1 s> 10 goto l0_%=;				\
+	r1 s%%= -11;					\
+	if r1 s< -8 goto l1_%=;				\
+	if r1 s> 10 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, zero divisor")
+__success __retval(0) __log_level(2)
+__msg("r1 s%= r2 {{.*}}; R1=scalar(smin=smin32=-8,smax=smax32=10) R2=0")
+__naked void smod64_zero_divisor(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	if r1 s< -8 goto l0_%=;				\
+	if r1 s> 10 goto l0_%=;				\
+	r2 = 0;						\
+	r1 s%%= r2;					\
+	if r1 s< -8 goto l1_%=;				\
+	if r1 s> 10 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, overflow (S64_MIN%-1)")
+__success __retval(0) __log_level(2)
+__msg("r1 s%= -1 {{.*}}; R1=0")
+__naked void smod64_overflow_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	r1 = r0;					\
+	r2 = %[llong_min] ll;				\
+	r2 += 10;					\
+	if r1 s> r2 goto l0_%=;				\
+	r1 s%%= -1;					\
+	if r1 != 0 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm_const(llong_min, LLONG_MIN),
+	  __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, overflow (S64_MIN%-1), constant dividend")
+__success __retval(0) __log_level(2)
+__msg("r1 s%= -1 {{.*}}; R1=0")
+__naked void smod64_overflow_2(void)
+{
+	asm volatile ("					\
+	r1 = %[llong_min] ll;				\
+	r1 s%%= -1;					\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u64 *)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm_const(llong_min, LLONG_MIN)
+	: __clobber_all);
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c b/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c
index 1204fbc58178..e7dae0cf9c17 100644
--- a/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c
+++ b/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c
@@ -72,7 +72,7 @@ int trusted_task_arg_nonnull_fail1(void *ctx)
 
 SEC("?tp_btf/task_newtask")
 __failure __log_level(2)
-__msg("R1 type=ptr_or_null_ expected=ptr_, trusted_ptr_, rcu_ptr_")
+__msg("R1 type=trusted_ptr_or_null_ expected=ptr_, trusted_ptr_, rcu_ptr_")
 __msg("Caller passes invalid args into func#1 ('subprog_trusted_task_nonnull')")
 int trusted_task_arg_nonnull_fail2(void *ctx)
 {
diff --git a/tools/testing/selftests/bpf/progs/verifier_helper_restricted.c b/tools/testing/selftests/bpf/progs/verifier_helper_restricted.c
index 059aa716e3d0..889c9b78b912 100644
--- a/tools/testing/selftests/bpf/progs/verifier_helper_restricted.c
+++ b/tools/testing/selftests/bpf/progs/verifier_helper_restricted.c
@@ -17,17 +17,6 @@ struct {
 	__type(value, struct val);
 } map_spin_lock SEC(".maps");
 
-struct timer {
-	struct bpf_timer t;
-};
-
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, 1);
-	__type(key, int);
-	__type(value, struct timer);
-} map_timer SEC(".maps");
-
 SEC("kprobe")
 __description("bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_KPROBE")
 __failure __msg("program of this type cannot use helper bpf_ktime_get_coarse_ns")
@@ -85,106 +74,6 @@ __naked void bpf_prog_type_raw_tracepoint_1(void)
 }
 
 SEC("kprobe")
-__description("bpf_timer_init isn restricted in BPF_PROG_TYPE_KPROBE")
-__failure __msg("tracing progs cannot use bpf_timer yet")
-__naked void in_bpf_prog_type_kprobe_2(void)
-{
-	asm volatile ("					\
-	r2 = r10;					\
-	r2 += -8;					\
-	r1 = 0;						\
-	*(u64*)(r2 + 0) = r1;				\
-	r1 = %[map_timer] ll;				\
-	call %[bpf_map_lookup_elem];			\
-	if r0 == 0 goto l0_%=;				\
-	r1 = r0;					\
-	r2 = %[map_timer] ll;				\
-	r3 = 1;						\
-l0_%=:	call %[bpf_timer_init];				\
-	exit;						\
-"	:
-	: __imm(bpf_map_lookup_elem),
-	  __imm(bpf_timer_init),
-	  __imm_addr(map_timer)
-	: __clobber_all);
-}
-
-SEC("perf_event")
-__description("bpf_timer_init is forbidden in BPF_PROG_TYPE_PERF_EVENT")
-__failure __msg("tracing progs cannot use bpf_timer yet")
-__naked void bpf_prog_type_perf_event_2(void)
-{
-	asm volatile ("					\
-	r2 = r10;					\
-	r2 += -8;					\
-	r1 = 0;						\
-	*(u64*)(r2 + 0) = r1;				\
-	r1 = %[map_timer] ll;				\
-	call %[bpf_map_lookup_elem];			\
-	if r0 == 0 goto l0_%=;				\
-	r1 = r0;					\
-	r2 = %[map_timer] ll;				\
-	r3 = 1;						\
-l0_%=:	call %[bpf_timer_init];				\
-	exit;						\
-"	:
-	: __imm(bpf_map_lookup_elem),
-	  __imm(bpf_timer_init),
-	  __imm_addr(map_timer)
-	: __clobber_all);
-}
-
-SEC("tracepoint")
-__description("bpf_timer_init is forbidden in BPF_PROG_TYPE_TRACEPOINT")
-__failure __msg("tracing progs cannot use bpf_timer yet")
-__naked void in_bpf_prog_type_tracepoint_2(void)
-{
-	asm volatile ("					\
-	r2 = r10;					\
-	r2 += -8;					\
-	r1 = 0;						\
-	*(u64*)(r2 + 0) = r1;				\
-	r1 = %[map_timer] ll;				\
-	call %[bpf_map_lookup_elem];			\
-	if r0 == 0 goto l0_%=;				\
-	r1 = r0;					\
-	r2 = %[map_timer] ll;				\
-	r3 = 1;						\
-l0_%=:	call %[bpf_timer_init];				\
-	exit;						\
-"	:
-	: __imm(bpf_map_lookup_elem),
-	  __imm(bpf_timer_init),
-	  __imm_addr(map_timer)
-	: __clobber_all);
-}
-
-SEC("raw_tracepoint")
-__description("bpf_timer_init is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT")
-__failure __msg("tracing progs cannot use bpf_timer yet")
-__naked void bpf_prog_type_raw_tracepoint_2(void)
-{
-	asm volatile ("					\
-	r2 = r10;					\
-	r2 += -8;					\
-	r1 = 0;						\
-	*(u64*)(r2 + 0) = r1;				\
-	r1 = %[map_timer] ll;				\
-	call %[bpf_map_lookup_elem];			\
-	if r0 == 0 goto l0_%=;				\
-	r1 = r0;					\
-	r2 = %[map_timer] ll;				\
-	r3 = 1;						\
-l0_%=:	call %[bpf_timer_init];				\
-	exit;						\
-"	:
-	: __imm(bpf_map_lookup_elem),
-	  __imm(bpf_timer_init),
-	  __imm_addr(map_timer)
-	: __clobber_all);
-}
-
-SEC("kprobe")
 __description("bpf_spin_lock is forbidden in BPF_PROG_TYPE_KPROBE")
 __failure __msg("tracing progs cannot use bpf_spin_lock yet")
 __naked void in_bpf_prog_type_kprobe_3(void)
diff --git a/tools/testing/selftests/bpf/progs/verifier_jit_inline.c b/tools/testing/selftests/bpf/progs/verifier_jit_inline.c
new file mode 100644
index 000000000000..4ea254063646
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_jit_inline.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("fentry/bpf_fentry_test1")
+__success __retval(0)
+__arch_x86_64
+__jited("	addq	%gs:{{.*}}, %rax")
+__arch_arm64
+__jited("	mrs	x7, SP_EL0")
+int inline_bpf_get_current_task(void)
+{
+	bpf_get_current_task();
+
+	return 0;
+}
+
+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 a509cad97e69..1fce7a7e8d03 100644
--- a/tools/testing/selftests/bpf/progs/verifier_kfunc_prog_types.c
+++ b/tools/testing/selftests/bpf/progs/verifier_kfunc_prog_types.c
@@ -32,7 +32,7 @@ static void task_kfunc_load_test(void)
 }
 
 SEC("raw_tp")
-__failure __msg("calling kernel function")
+__success
 int BPF_PROG(task_kfunc_raw_tp)
 {
 	task_kfunc_load_test();
@@ -86,7 +86,7 @@ static void cgrp_kfunc_load_test(void)
 }
 
 SEC("raw_tp")
-__failure __msg("calling kernel function")
+__success
 int BPF_PROG(cgrp_kfunc_raw_tp)
 {
 	cgrp_kfunc_load_test();
@@ -138,7 +138,7 @@ static void cpumask_kfunc_load_test(void)
 }
 
 SEC("raw_tp")
-__failure __msg("calling kernel function")
+__success
 int BPF_PROG(cpumask_kfunc_raw_tp)
 {
 	cpumask_kfunc_load_test();
diff --git a/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c
index 8f755d2464cf..2ef346c827c2 100644
--- a/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c
+++ b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.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"
 
@@ -18,9 +19,9 @@ __naked void scalars(void)
 	r4 = r1;				\
 	w2 += 0x7FFFFFFF;			\
 	w4 += 0;				\
-	if r2 == 0 goto l1;			\
+	if r2 == 0 goto l0_%=;			\
 	exit;					\
-l1:						\
+l0_%=:						\
 	r4 >>= 63;				\
 	r3 = 1;					\
 	r3 -= r4;				\
@@ -31,4 +32,335 @@ l1:						\
 "	::: __clobber_all);
 }
 
+/*
+ * Test that sync_linked_regs() preserves register IDs.
+ *
+ * The sync_linked_regs() function copies bounds from known_reg to linked
+ * registers. When doing so, it must preserve each register's original id
+ * to allow subsequent syncs from the same source to work correctly.
+ *
+ */
+SEC("socket")
+__success
+__naked void sync_linked_regs_preserves_id(void)
+{
+	asm volatile ("						\
+	call %[bpf_get_prandom_u32];				\
+	r0 &= 0xff;	/* r0 in [0, 255] */			\
+	r1 = r0;	/* r0, r1 linked with id 1 */		\
+	r1 += 4;	/* r1 has id=1 and off=4 in [4, 259] */ \
+	if r1 < 10 goto l0_%=;					\
+	/* r1 in [10, 259], r0 synced to [6, 255] */		\
+	r2 = r0;	/* r2 has id=1 and in [6, 255] */	\
+	if r1 < 14 goto l0_%=;					\
+	/* r1 in [14, 259], r0 synced to [10, 255] */		\
+	if r0 >= 10 goto l0_%=;					\
+	/* Never executed */					\
+	r0 /= 0;						\
+l0_%=:								\
+	r0 = 0;							\
+	exit;							\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__success
+__naked void scalars_neg(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0xff;					\
+	r1 = r0;					\
+	r1 += -4;					\
+	if r1 s< 0 goto l0_%=;				\
+	if r0 != 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* Same test but using BPF_SUB instead of BPF_ADD with negative immediate */
+SEC("socket")
+__success
+__naked void scalars_neg_sub(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0xff;					\
+	r1 = r0;					\
+	r1 -= 4;					\
+	if r1 s< 0 goto l0_%=;				\
+	if r0 != 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* alu32 with negative offset */
+SEC("socket")
+__success
+__naked void scalars_neg_alu32_add(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w0 &= 0xff;					\
+	w1 = w0;					\
+	w1 += -4;					\
+	if w1 s< 0 goto l0_%=;				\
+	if w0 != 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* alu32 with negative offset using SUB */
+SEC("socket")
+__success
+__naked void scalars_neg_alu32_sub(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w0 &= 0xff;					\
+	w1 = w0;					\
+	w1 -= 4;					\
+	if w1 s< 0 goto l0_%=;				\
+	if w0 != 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* Positive offset: r1 = r0 + 4, then if r1 >= 6, r0 >= 2, so r0 != 0 */
+SEC("socket")
+__success
+__naked void scalars_pos(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0xff;					\
+	r1 = r0;					\
+	r1 += 4;					\
+	if r1 < 6 goto l0_%=;				\
+	if r0 != 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* SUB with negative immediate: r1 -= -4 is equivalent to r1 += 4 */
+SEC("socket")
+__success
+__naked void scalars_sub_neg_imm(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0xff;					\
+	r1 = r0;					\
+	r1 -= -4;					\
+	if r1 < 6 goto l0_%=;				\
+	if r0 != 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* Double ADD clears the ID (can't accumulate offsets) */
+SEC("socket")
+__failure
+__msg("div by zero")
+__naked void scalars_double_add(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0xff;					\
+	r1 = r0;					\
+	r1 += 2;					\
+	r1 += 2;					\
+	if r1 < 6 goto l0_%=;				\
+	if r0 != 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/*
+ * Test that sync_linked_regs() correctly handles large offset differences.
+ * r1.off = S32_MIN, r2.off = 1, delta = S32_MIN - 1 requires 64-bit math.
+ */
+SEC("socket")
+__success
+__naked void scalars_sync_delta_overflow(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0xff;					\
+	r1 = r0;					\
+	r2 = r0;					\
+	r1 += %[s32_min];				\
+	r2 += 1;					\
+	if r2 s< 100 goto l0_%=;			\
+	if r1 s< 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  [s32_min]"i"(INT_MIN)
+	: __clobber_all);
+}
+
+/*
+ * Another large delta case: r1.off = S32_MAX, r2.off = -1.
+ * delta = S32_MAX - (-1) = S32_MAX + 1 requires 64-bit math.
+ */
+SEC("socket")
+__success
+__naked void scalars_sync_delta_overflow_large_range(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0xff;					\
+	r1 = r0;					\
+	r2 = r0;					\
+	r1 += %[s32_max];				\
+	r2 += -1;					\
+	if r2 s< 0 goto l0_%=;				\
+	if r1 s>= 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  [s32_max]"i"(INT_MAX)
+	: __clobber_all);
+}
+
+/*
+ * Test linked scalar tracking with alu32 and large positive offset (0x7FFFFFFF).
+ * After w1 += 0x7FFFFFFF, w1 wraps to negative for any r0 >= 1.
+ * If w1 is signed-negative, then r0 >= 1, so r0 != 0.
+ */
+SEC("socket")
+__success
+__naked void scalars_alu32_big_offset(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w0 &= 0xff;					\
+	w1 = w0;					\
+	w1 += 0x7FFFFFFF;				\
+	if w1 s>= 0 goto l0_%=;				\
+	if w0 != 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__failure
+__msg("div by zero")
+__naked void scalars_alu32_basic(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	w1 += 1;					\
+	if r1 > 10 goto 1f;				\
+	r0 >>= 32;					\
+	if r0 == 0 goto 1f;				\
+	r0 /= 0;					\
+1:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/*
+ * Test alu32 linked register tracking with wrapping.
+ * R0 is bounded to [0xffffff00, 0xffffffff] (high 32-bit values)
+ * w1 += 0x100 causes R1 to wrap to [0, 0xff]
+ *
+ * After sync_linked_regs, if bounds are computed correctly:
+ *   R0 should be [0x00000000_ffffff00, 0x00000000_ffffff80]
+ *   R0 >> 32 == 0, so div by zero is unreachable
+ *
+ * If bounds are computed incorrectly (64-bit underflow):
+ *   R0 becomes [0xffffffff_ffffff00, 0xffffffff_ffffff80]
+ *   R0 >> 32 == 0xffffffff != 0, so div by zero is reachable
+ */
+SEC("socket")
+__success
+__naked void scalars_alu32_wrap(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w0 |= 0xffffff00;				\
+	r1 = r0;					\
+	w1 += 0x100;					\
+	if r1 > 0x80 goto l0_%=;			\
+	r2 = r0;					\
+	r2 >>= 32;					\
+	if r2 == 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__success
+void alu32_negative_offset(void)
+{
+	volatile char path[5];
+	volatile int offset = bpf_get_prandom_u32();
+	int off = offset;
+
+	if (off >= 5 && off < 10)
+		path[off - 5] = '.';
+
+	/* So compiler doesn't say: error: variable 'path' set but not used */
+	__sink(path[0]);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_lsm.c b/tools/testing/selftests/bpf/progs/verifier_lsm.c
index 6af9100a37ff..38e8e9176862 100644
--- a/tools/testing/selftests/bpf/progs/verifier_lsm.c
+++ b/tools/testing/selftests/bpf/progs/verifier_lsm.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/bpf.h>
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 #include "bpf_misc.h"
 
 SEC("lsm/file_permission")
@@ -159,4 +160,32 @@ __naked int disabled_hook_test3(void *ctx)
 	::: __clobber_all);
 }
 
+SEC("lsm/mmap_file")
+__description("not null checking nullable pointer in bpf_lsm_mmap_file")
+__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'")
+int BPF_PROG(no_null_check, struct file *file)
+{
+	struct inode *inode;
+
+	inode = file->f_inode;
+	__sink(inode);
+
+	return 0;
+}
+
+SEC("lsm/mmap_file")
+__description("null checking nullable pointer in bpf_lsm_mmap_file")
+__success
+int BPF_PROG(null_check, struct file *file)
+{
+	struct inode *inode;
+
+	if (file) {
+		inode = file->f_inode;
+		__sink(inode);
+	}
+
+	return 0;
+}
+
 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 c0ce690ddb68..3072fee9a448 100644
--- a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
+++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
@@ -715,6 +715,51 @@ __naked void ignore_unique_scalar_ids_old(void)
 	: __clobber_all);
 }
 
+/* Check that two registers with 0 scalar IDs in a verified state can be mapped
+ * to the same scalar ID in current state.
+ */
+SEC("socket")
+__success __log_level(2)
+/* The states should be equivalent on reaching insn 12.
+ */
+__msg("12: safe")
+__msg("processed 17 insns")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void two_nil_old_ids_one_cur_id(void)
+{
+	asm volatile (
+	/* Give unique scalar IDs to r{6,7} */
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	"r6 = r0;"
+	"r6 *= 1;"
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	"r7 = r0;"
+	"r7 *= 1;"
+	"r0 = 0;"
+	/* Maybe make r{6,7} IDs identical */
+	"if r6 > r7 goto l0_%=;"
+	"goto l1_%=;"
+"l0_%=:"
+	"r6 = r7;"
+"l1_%=:"
+	/* Mark r{6,7} precise.
+	 * Get here in two states:
+	 * - first:  r6{.id=0}, r7{.id=0} (cached state)
+	 * - second: r6{.id=A}, r7{.id=A}
+	 * Verifier considers such states equivalent.
+	 * Thus "exit;" would be verified only once.
+	 */
+	"r2 = r10;"
+	"r2 += r6;"
+	"r2 += r7;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
 /* Check that two different scalar IDs in a verified state can't be
  * mapped to the same scalar ID in current state.
  */
@@ -723,9 +768,9 @@ __success __log_level(2)
 /* The exit instruction should be reachable from two states,
  * use two matches and "processed .. insns" to ensure this.
  */
-__msg("13: (95) exit")
-__msg("13: (95) exit")
-__msg("processed 18 insns")
+__msg("15: (95) exit")
+__msg("15: (95) exit")
+__msg("processed 20 insns")
 __flag(BPF_F_TEST_STATE_FREQ)
 __naked void two_old_ids_one_cur_id(void)
 {
@@ -734,9 +779,11 @@ __naked void two_old_ids_one_cur_id(void)
 	"call %[bpf_ktime_get_ns];"
 	"r0 &= 0xff;"
 	"r6 = r0;"
+	"r8 = r0;"
 	"call %[bpf_ktime_get_ns];"
 	"r0 &= 0xff;"
 	"r7 = r0;"
+	"r9 = r0;"
 	"r0 = 0;"
 	/* Maybe make r{6,7} IDs identical */
 	"if r6 > r7 goto l0_%=;"
diff --git a/tools/testing/selftests/bpf/progs/verifier_subreg.c b/tools/testing/selftests/bpf/progs/verifier_subreg.c
index 8613ea160dcd..be328100ba53 100644
--- a/tools/testing/selftests/bpf/progs/verifier_subreg.c
+++ b/tools/testing/selftests/bpf/progs/verifier_subreg.c
@@ -532,6 +532,74 @@ __naked void arsh32_imm_zero_extend_check(void)
 }
 
 SEC("socket")
+__description("arsh32 imm sign positive extend check")
+__success __retval(0)
+__log_level(2)
+__msg("2: (57) r6 &= 4095                    ; R6=scalar(smin=smin32=0,smax=umax=smax32=umax32=4095,var_off=(0x0; 0xfff))")
+__msg("3: (67) r6 <<= 32                     ; R6=scalar(smin=smin32=0,smax=umax=0xfff00000000,smax32=umax32=0,var_off=(0x0; 0xfff00000000))")
+__msg("4: (c7) r6 s>>= 32                    ; R6=scalar(smin=smin32=0,smax=umax=smax32=umax32=4095,var_off=(0x0; 0xfff))")
+__naked void arsh32_imm_sign_extend_positive_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r6 = r0;					\
+	r6 &= 4095;					\
+	r6 <<= 32;					\
+	r6 s>>= 32;					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("arsh32 imm sign negative extend check")
+__success __retval(0)
+__log_level(2)
+__msg("3: (17) r6 -= 4095                    ; R6=scalar(smin=smin32=-4095,smax=smax32=0)")
+__msg("4: (67) r6 <<= 32                     ; R6=scalar(smin=0xfffff00100000000,smax=smax32=umax32=0,umax=0xffffffff00000000,smin32=0,var_off=(0x0; 0xffffffff00000000))")
+__msg("5: (c7) r6 s>>= 32                    ; R6=scalar(smin=smin32=-4095,smax=smax32=0)")
+__naked void arsh32_imm_sign_extend_negative_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r6 = r0;					\
+	r6 &= 4095;					\
+	r6 -= 4095;					\
+	r6 <<= 32;					\
+	r6 s>>= 32;					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("arsh32 imm sign extend check")
+__success __retval(0)
+__log_level(2)
+__msg("3: (17) r6 -= 2047                    ; R6=scalar(smin=smin32=-2047,smax=smax32=2048)")
+__msg("4: (67) r6 <<= 32                     ; R6=scalar(smin=0xfffff80100000000,smax=0x80000000000,umax=0xffffffff00000000,smin32=0,smax32=umax32=0,var_off=(0x0; 0xffffffff00000000))")
+__msg("5: (c7) r6 s>>= 32                    ; R6=scalar(smin=smin32=-2047,smax=smax32=2048)")
+__naked void arsh32_imm_sign_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r6 = r0;					\
+	r6 &= 4095;					\
+	r6 -= 2047;					\
+	r6 <<= 32;					\
+	r6 s>>= 32;					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
 __description("end16 (to_le) reg zero extend check")
 __success __success_unpriv __retval(0)
 __naked void le_reg_zero_extend_check_1(void)
@@ -670,4 +738,89 @@ __naked void ldx_w_zero_extend_check(void)
 	: __clobber_all);
 }
 
+SEC("socket")
+__success __success_unpriv __retval(0)
+__naked void arsh_31_and(void)
+{
+	/* Below is what LLVM generates in cilium's bpf_wiregard.o */
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w2 = w0;					\
+	w2 s>>= 31;					\
+	w2 &= -134; /* w2 becomes 0 or -134 */		\
+	if w2 s> -1 goto +2;				\
+	/* Branch always taken because w2 = -134 */	\
+	if w2 != -136 goto +1;				\
+	w0 /= 0;					\
+	w0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__success __success_unpriv __retval(0)
+__naked void arsh_63_and(void)
+{
+	/* Copy of arsh_31 with s/w/r/ */
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r2 = r0;					\
+	r2 <<= 32;					\
+	r2 s>>= 63;					\
+	r2 &= -134;					\
+	if r2 s> -1 goto +2;				\
+	/* Branch always taken because w2 = -134 */	\
+	if r2 != -136 goto +1;				\
+	r0 /= 0;					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__success __success_unpriv __retval(0)
+__naked void arsh_31_or(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w2 = w0;					\
+	w2 s>>= 31;					\
+	w2 |= 134; /* w2 becomes -1 or 134 */		\
+	if w2 s> -1 goto +2;				\
+	/* Branch always taken because w2 = -1 */	\
+	if w2 == -1 goto +1;				\
+	w0 /= 0;					\
+	w0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__success __success_unpriv __retval(0)
+__naked void arsh_63_or(void)
+{
+	/* Copy of arsh_31 with s/w/r/ */
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r2 = r0;					\
+	r2 <<= 32;					\
+	r2 s>>= 63;					\
+	r2 |= 134; /* r2 becomes -1 or 134 */		\
+	if r2 s> -1 goto +2;				\
+	/* Branch always taken because w2 = -1 */	\
+	if r2 == -1 goto +1;				\
+	r0 /= 0;					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_unpriv.c b/tools/testing/selftests/bpf/progs/verifier_unpriv.c
index 28b4f7035ceb..8ee1243e62a8 100644
--- a/tools/testing/selftests/bpf/progs/verifier_unpriv.c
+++ b/tools/testing/selftests/bpf/progs/verifier_unpriv.c
@@ -950,4 +950,26 @@ l3_%=:	r0 = 0;						\
 "	::: __clobber_all);
 }
 
+SEC("socket")
+__description("unpriv: nospec after dead stack write in helper")
+__success __success_unpriv
+__retval(0)
+/* Dead code sanitizer rewrites the call to `goto -1`. */
+__naked void unpriv_dead_helper_stack_write_nospec_result(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	if r0 != 1 goto l0_%=;				\
+	r2 = 0;						\
+	r3 = r10;					\
+	r3 += -16;					\
+	r4 = 4;						\
+	r5 = 0;						\
+	call %[bpf_skb_load_bytes_relative];		\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes_relative)
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c
index 2129e4353fd9..4d8273c258d5 100644
--- a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c
+++ b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c
@@ -173,14 +173,15 @@ __naked void flow_keys_illegal_variable_offset_alu(void)
 	asm volatile("					\
 	r6 = r1;					\
 	r7 = *(u64*)(r6 + %[flow_keys_off]);		\
-	r8 = 8;						\
-	r8 /= 1;					\
+	call %[bpf_get_prandom_u32];			\
+	r8 = r0;					\
 	r8 &= 8;					\
 	r7 += r8;					\
 	r0 = *(u64*)(r7 + 0);				\
 	exit;						\
 "	:
-	: __imm_const(flow_keys_off, offsetof(struct __sk_buff, flow_keys))
+	: __imm_const(flow_keys_off, offsetof(struct __sk_buff, flow_keys)),
+	  __imm(bpf_get_prandom_u32)
 	: __clobber_all);
 }
 
diff --git a/tools/testing/selftests/bpf/progs/verifier_xdp.c b/tools/testing/selftests/bpf/progs/verifier_xdp.c
index 50768ed179b3..7dc9226aeb34 100644
--- a/tools/testing/selftests/bpf/progs/verifier_xdp.c
+++ b/tools/testing/selftests/bpf/progs/verifier_xdp.c
@@ -5,6 +5,14 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, __u64);
+	__uint(map_flags, BPF_F_RDONLY_PROG);
+} map_array_ro SEC(".maps");
+
 SEC("xdp")
 __description("XDP, using ifindex from netdev")
 __success __retval(1)
@@ -21,4 +29,31 @@ l0_%=:	exit;						\
 	: __clobber_all);
 }
 
+SEC("xdp")
+__description("XDP, using xdp_store_bytes from RO map")
+__success __retval(0)
+__naked void xdp_store_bytes_from_ro_map(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;                                         \
+	*(u64*)(r10 - 8) = r1;                          \
+	r2 = r10;                                       \
+	r2 += -8;                                       \
+	r1 = %[map_array_ro] ll;                        \
+	call %[bpf_map_lookup_elem];                    \
+	if r0 == 0 goto l0_%=;                          \
+	r1 = r6;					\
+	r2 = 0;						\
+	r3 = r0;					\
+	r4 = 8;						\
+	call %[bpf_xdp_store_bytes];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_xdp_store_bytes),
+	  __imm_addr(map_array_ro)
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/wq_failures.c b/tools/testing/selftests/bpf/progs/wq_failures.c
index d06f6d40594a..3767f5595bbc 100644
--- a/tools/testing/selftests/bpf/progs/wq_failures.c
+++ b/tools/testing/selftests/bpf/progs/wq_failures.c
@@ -97,7 +97,7 @@ __failure
 /* check that the first argument of bpf_wq_set_callback()
  * is a correct bpf_wq pointer.
  */
-__msg(": (85) call bpf_wq_set_callback_impl#") /* anchor message */
+__msg(": (85) call bpf_wq_set_callback#") /* anchor message */
 __msg("arg#0 doesn't point to a map value")
 long test_wrong_wq_pointer(void *ctx)
 {
@@ -123,7 +123,7 @@ __failure
 /* check that the first argument of bpf_wq_set_callback()
  * is a correct bpf_wq pointer.
  */
-__msg(": (85) call bpf_wq_set_callback_impl#") /* anchor message */
+__msg(": (85) call bpf_wq_set_callback#") /* anchor message */
 __msg("off 1 doesn't point to 'struct bpf_wq' that is at 0")
 long test_wrong_wq_pointer_offset(void *ctx)
 {
diff --git a/tools/testing/selftests/bpf/test_bpftool_map.sh b/tools/testing/selftests/bpf/test_bpftool_map.sh
deleted file mode 100755
index 515b1df0501e..000000000000
--- a/tools/testing/selftests/bpf/test_bpftool_map.sh
+++ /dev/null
@@ -1,398 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
-TESTNAME="bpftool_map"
-BPF_FILE="security_bpf_map.bpf.o"
-BPF_ITER_FILE="bpf_iter_map_elem.bpf.o"
-PROTECTED_MAP_NAME="prot_map"
-NOT_PROTECTED_MAP_NAME="not_prot_map"
-BPF_FS_TMP_PARENT="/tmp"
-BPF_FS_PARENT=$(awk '$3 == "bpf" {print $2; exit}' /proc/mounts)
-BPF_FS_PARENT=${BPF_FS_PARENT:-$BPF_FS_TMP_PARENT}
-# bpftool will mount bpf file system under BPF_DIR if it is not mounted
-# under BPF_FS_PARENT.
-BPF_DIR="$BPF_FS_PARENT/test_$TESTNAME"
-SCRIPT_DIR=$(dirname $(realpath "$0"))
-BPF_FILE_PATH="$SCRIPT_DIR/$BPF_FILE"
-BPF_ITER_FILE_PATH="$SCRIPT_DIR/$BPF_ITER_FILE"
-BPFTOOL_PATH="bpftool"
-# Assume the script is located under tools/testing/selftests/bpf/
-KDIR_ROOT_DIR=$(realpath "$SCRIPT_DIR"/../../../../)
-
-_cleanup()
-{
-	set +eu
-
-	# If BPF_DIR is a mount point this will not remove the mount point itself.
-	[ -d "$BPF_DIR" ] && rm -rf "$BPF_DIR" 2> /dev/null
-
-	# Unmount if BPF filesystem was temporarily created.
-	if [ "$BPF_FS_PARENT" = "$BPF_FS_TMP_PARENT" ]; then
-		# A loop and recursive unmount are required as bpftool might
-		# create multiple mounts. For example, a bind mount of the directory
-		# to itself. The bind mount is created to change mount propagation
-		# flags on an actual mount point.
-		max_attempts=3
-		attempt=0
-		while mountpoint -q "$BPF_DIR" && [ $attempt -lt $max_attempts ]; do
-			umount -R "$BPF_DIR" 2>/dev/null
-			attempt=$((attempt+1))
-		done
-
-		# The directory still exists. Remove it now.
-		[ -d "$BPF_DIR" ] && rm -rf "$BPF_DIR" 2>/dev/null
-	fi
-}
-
-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
-}
-
-check_root_privileges() {
-	if [ $(id -u) -ne 0 ]; then
-		echo "Need root privileges"
-		exit $ksft_skip
-	fi
-}
-
-# Function to verify bpftool path.
-# Parameters:
-#   $1: bpftool path
-verify_bpftool_path() {
-	local bpftool_path="$1"
-	if ! "$bpftool_path" version > /dev/null 2>&1; then
-		echo "Could not run test without bpftool"
-		exit $ksft_skip
-	fi
-}
-
-# Function to verify BTF support.
-# The test requires BTF support for fmod_ret programs.
-verify_btf_support() {
-	if [ ! -f /sys/kernel/btf/vmlinux ]; then
-		echo "Could not run test without BTF support"
-		exit $ksft_skip
-	fi
-}
-
-# Function to initialize map entries with keys [0..2] and values set to 0.
-# Parameters:
-#  $1: Map name
-#  $2: bpftool path
-initialize_map_entries() {
-	local map_name="$1"
-	local bpftool_path="$2"
-
-	for key in 0 1 2; do
-		"$bpftool_path" map update name "$map_name" key $key 0 0 0 value 0 0 0 $key
-	done
-}
-
-# Test read access to the map.
-# Parameters:
-#   $1: Name command (name/pinned)
-#   $2: Map name
-#   $3: bpftool path
-#   $4: key
-access_for_read() {
-	local name_cmd="$1"
-	local map_name="$2"
-	local bpftool_path="$3"
-	local key="$4"
-
-	# Test read access to the map.
-	if ! "$bpftool_path" map lookup "$name_cmd" "$map_name" key $key 1>/dev/null; then
-		echo " Read access to $key in $map_name failed"
-		exit 1
-	fi
-
-	# Test read access to map's BTF data.
-	if ! "$bpftool_path" btf dump map "$name_cmd" "$map_name" 1>/dev/null; then
-		echo " Read access to $map_name for BTF data failed"
-		exit 1
-	fi
-}
-
-# Test write access to the map.
-# Parameters:
-#   $1: Name command (name/pinned)
-#   $2: Map name
-#   $3: bpftool path
-#   $4: key
-#   $5: Whether write should succeed (true/false)
-access_for_write() {
-	local name_cmd="$1"
-	local map_name="$2"
-	local bpftool_path="$3"
-	local key="$4"
-	local write_should_succeed="$5"
-	local value="1 1 1 1"
-
-	if "$bpftool_path" map update "$name_cmd" "$map_name" key $key value \
-			$value 2>/dev/null; then
-		if [ "$write_should_succeed" = "false" ]; then
-			echo " Write access to $key in $map_name succeeded but should have failed"
-			exit 1
-		fi
-	else
-		if [ "$write_should_succeed" = "true" ]; then
-			echo " Write access to $key in $map_name failed but should have succeeded"
-			exit 1
-		fi
-	fi
-}
-
-# Test entry deletion for the map.
-# Parameters:
-#   $1: Name command (name/pinned)
-#   $2: Map name
-#   $3: bpftool path
-#   $4: key
-#   $5: Whether write should succeed (true/false)
-access_for_deletion() {
-	local name_cmd="$1"
-	local map_name="$2"
-	local bpftool_path="$3"
-	local key="$4"
-	local write_should_succeed="$5"
-	local value="1 1 1 1"
-
-	# Test deletion by key for the map.
-	# Before deleting, check the key exists.
-	if ! "$bpftool_path" map lookup "$name_cmd" "$map_name" key $key 1>/dev/null; then
-		echo " Key $key does not exist in $map_name"
-		exit 1
-	fi
-
-	# Delete by key.
-	if "$bpftool_path" map delete "$name_cmd" "$map_name" key $key 2>/dev/null; then
-		if [ "$write_should_succeed" = "false" ]; then
-			echo " Deletion for $key in $map_name succeeded but should have failed"
-			exit 1
-		fi
-	else
-		if [ "$write_should_succeed" = "true" ]; then
-			echo " Deletion for $key in $map_name failed but should have succeeded"
-			exit 1
-		fi
-	fi
-
-	# After deleting, check the entry existence according to the expected status.
-	if "$bpftool_path" map lookup "$name_cmd" "$map_name" key $key 1>/dev/null; then
-		if [ "$write_should_succeed" = "true" ]; then
-			echo " Key $key for $map_name was not deleted but should have been deleted"
-			exit 1
-		fi
-	else
-		if [ "$write_should_succeed" = "false" ]; then
-			echo "Key $key for $map_name was deleted but should have not been deleted"
-			exit 1
-		fi
-	fi
-
-	# Test creation of map's deleted entry, if deletion was successful.
-	# Otherwise, the entry exists.
-	if "$bpftool_path" map update "$name_cmd" "$map_name" key $key value \
-				$value 2>/dev/null; then
-		if [ "$write_should_succeed" = "false" ]; then
-			echo " Write access to $key in $map_name succeeded after deletion attempt but should have failed"
-			exit 1
-		fi
-	else
-		if [ "$write_should_succeed" = "true" ]; then
-			echo " Write access to $key in $map_name failed after deletion attempt but should have succeeded"
-			exit 1
-		fi
-	fi
-}
-
-# Test map elements iterator.
-# Parameters:
-#   $1: Name command (name/pinned)
-#   $2: Map name
-#   $3: bpftool path
-#   $4: BPF_DIR
-#   $5: bpf iterator object file path
-iterate_map_elem() {
-	local name_cmd="$1"
-	local map_name="$2"
-	local bpftool_path="$3"
-	local bpf_dir="$4"
-	local bpf_file="$5"
-	local pin_path="$bpf_dir/map_iterator"
-
-	"$bpftool_path" iter pin "$bpf_file" "$pin_path" map "$name_cmd" "$map_name"
-	if [ ! -f "$pin_path" ]; then
-		echo " Failed to pin iterator to $pin_path"
-		exit 1
-	fi
-
-	cat "$pin_path" 1>/dev/null
-	rm "$pin_path" 2>/dev/null
-}
-
-# Function to test map access with configurable write expectations
-# Parameters:
-#   $1: Name command (name/pinned)
-#   $2: Map name
-#   $3: bpftool path
-#   $4: key for rw
-#   $5: key to delete
-#   $6: Whether write should succeed (true/false)
-#   $7: BPF_DIR
-#   $8: bpf iterator object file path
-access_map() {
-	local name_cmd="$1"
-	local map_name="$2"
-	local bpftool_path="$3"
-	local key_for_rw="$4"
-	local key_to_del="$5"
-	local write_should_succeed="$6"
-	local bpf_dir="$7"
-	local bpf_iter_file_path="$8"
-
-	access_for_read "$name_cmd" "$map_name" "$bpftool_path" "$key_for_rw"
-	access_for_write "$name_cmd" "$map_name" "$bpftool_path" "$key_for_rw" \
-		"$write_should_succeed"
-	access_for_deletion "$name_cmd" "$map_name" "$bpftool_path" "$key_to_del" \
-		"$write_should_succeed"
-	iterate_map_elem "$name_cmd" "$map_name" "$bpftool_path" "$bpf_dir" \
-		"$bpf_iter_file_path"
-}
-
-# Function to test map access with configurable write expectations
-# Parameters:
-#   $1: Map name
-#   $2: bpftool path
-#   $3: BPF_DIR
-#   $4: Whether write should succeed (true/false)
-#   $5: bpf iterator object file path
-test_map_access() {
-	local map_name="$1"
-	local bpftool_path="$2"
-	local bpf_dir="$3"
-	local pin_path="$bpf_dir/${map_name}_pinned"
-	local write_should_succeed="$4"
-	local bpf_iter_file_path="$5"
-
-	# Test access to the map by name.
-	access_map "name" "$map_name" "$bpftool_path" "0 0 0 0" "1 0 0 0" \
-		"$write_should_succeed" "$bpf_dir" "$bpf_iter_file_path"
-
-	# Pin the map to the BPF filesystem
-	"$bpftool_path" map pin name "$map_name" "$pin_path"
-	if [ ! -e "$pin_path" ]; then
-		echo " Failed to pin $map_name"
-		exit 1
-	fi
-
-	# Test access to the pinned map.
-	access_map "pinned" "$pin_path" "$bpftool_path" "0 0 0 0" "2 0 0 0" \
-		"$write_should_succeed" "$bpf_dir" "$bpf_iter_file_path"
-}
-
-# Function to test map creation and map-of-maps
-# Parameters:
-#   $1: bpftool path
-#   $2: BPF_DIR
-test_map_creation_and_map_of_maps() {
-	local bpftool_path="$1"
-	local bpf_dir="$2"
-	local outer_map_name="outer_map_tt"
-	local inner_map_name="inner_map_tt"
-
-	"$bpftool_path" map create "$bpf_dir/$inner_map_name" type array key 4 \
-		value 4 entries 4 name "$inner_map_name"
-	if [ ! -f "$bpf_dir/$inner_map_name" ]; then
-		echo " Failed to create inner map file at $bpf_dir/$outer_map_name"
-		return 1
-	fi
-
-	"$bpftool_path" map create "$bpf_dir/$outer_map_name" type hash_of_maps \
-		key 4 value 4 entries 2 name "$outer_map_name" inner_map name "$inner_map_name"
-	if [ ! -f "$bpf_dir/$outer_map_name" ]; then
-		echo " Failed to create outer map file at $bpf_dir/$outer_map_name"
-		return 1
-	fi
-
-	# Add entries to the outer map by name and by pinned path.
-	"$bpftool_path" map update pinned "$bpf_dir/$outer_map_name" key 0 0 0 0 \
-		value pinned "$bpf_dir/$inner_map_name"
-	"$bpftool_path" map update name "$outer_map_name" key 1 0 0 0 value \
-		name "$inner_map_name"
-
-	# The outer map should be full by now.
-	# The following map update command is expected to fail.
-	if "$bpftool_path" map update name "$outer_map_name" key 2 0 0 0 value name \
-		"$inner_map_name" 2>/dev/null; then
-		echo " Update for $outer_map_name succeeded but should have failed"
-		exit 1
-	fi
-}
-
-# Function to test map access with the btf list command
-# Parameters:
-#   $1: bpftool path
-test_map_access_with_btf_list() {
-	local bpftool_path="$1"
-
-	# The btf list command iterates over maps for
-	# loaded BPF programs.
-	if ! "$bpftool_path" btf list 1>/dev/null; then
-		echo " Failed to access btf data"
-		exit 1
-	fi
-}
-
-set -eu
-
-trap cleanup_skip EXIT
-
-check_root_privileges
-
-verify_bpftool_path "$BPFTOOL_PATH"
-
-verify_btf_support
-
-trap cleanup EXIT
-
-# Load and attach the BPF programs to control maps access.
-"$BPFTOOL_PATH" prog loadall "$BPF_FILE_PATH" "$BPF_DIR" autoattach
-
-initialize_map_entries "$PROTECTED_MAP_NAME" "$BPFTOOL_PATH"
-initialize_map_entries "$NOT_PROTECTED_MAP_NAME" "$BPFTOOL_PATH"
-
-# Activate the map protection mechanism. Protection status is controlled
-# by a value stored in the prot_status_map at index 0.
-"$BPFTOOL_PATH" map update name prot_status_map key 0 0 0 0 value 1 0 0 0
-
-# Test protected map (write should fail).
-test_map_access "$PROTECTED_MAP_NAME" "$BPFTOOL_PATH" "$BPF_DIR" "false" \
- "$BPF_ITER_FILE_PATH"
-
-# Test not protected map (write should succeed).
-test_map_access "$NOT_PROTECTED_MAP_NAME" "$BPFTOOL_PATH" "$BPF_DIR" "true" \
- "$BPF_ITER_FILE_PATH"
-
-test_map_creation_and_map_of_maps "$BPFTOOL_PATH" "$BPF_DIR"
-
-test_map_access_with_btf_list "$BPFTOOL_PATH"
-
-exit 0
diff --git a/tools/testing/selftests/bpf/test_bpftool_metadata.sh b/tools/testing/selftests/bpf/test_bpftool_metadata.sh
deleted file mode 100755
index b5520692f41b..000000000000
--- a/tools/testing/selftests/bpf/test_bpftool_metadata.sh
+++ /dev/null
@@ -1,85 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
-BPF_FILE_USED="metadata_used.bpf.o"
-BPF_FILE_UNUSED="metadata_unused.bpf.o"
-
-TESTNAME=bpftool_metadata
-BPF_FS=$(awk '$3 == "bpf" {print $2; exit}' /proc/mounts)
-BPF_DIR=$BPF_FS/test_$TESTNAME
-
-_cleanup()
-{
-	set +e
-	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 $ksft_skip
-fi
-
-if [ -z "$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
-
-mkdir $BPF_DIR
-
-trap cleanup EXIT
-
-bpftool prog load $BPF_FILE_UNUSED $BPF_DIR/unused
-
-METADATA_PLAIN="$(bpftool prog)"
-echo "$METADATA_PLAIN" | grep 'a = "foo"' > /dev/null
-echo "$METADATA_PLAIN" | grep 'b = 1' > /dev/null
-
-bpftool prog --json | grep '"metadata":{"a":"foo","b":1}' > /dev/null
-
-bpftool map | grep 'metadata.rodata' > /dev/null
-
-rm $BPF_DIR/unused
-
-bpftool prog load $BPF_FILE_USED $BPF_DIR/used
-
-METADATA_PLAIN="$(bpftool prog)"
-echo "$METADATA_PLAIN" | grep 'a = "bar"' > /dev/null
-echo "$METADATA_PLAIN" | grep 'b = 2' > /dev/null
-
-bpftool prog --json | grep '"metadata":{"a":"bar","b":2}' > /dev/null
-
-bpftool map | grep 'metadata.rodata' > /dev/null
-
-rm $BPF_DIR/used
-
-exit 0
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod-events.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod-events.h
index aeef86b3da74..45a5e41f3a92 100644
--- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod-events.h
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod-events.h
@@ -63,6 +63,16 @@ BPF_TESTMOD_DECLARE_TRACE(bpf_testmod_test_writable_bare,
 	sizeof(struct bpf_testmod_test_writable_ctx)
 );
 
+DECLARE_TRACE(bpf_testmod_fentry_test1,
+	TP_PROTO(int a),
+	TP_ARGS(a)
+);
+
+DECLARE_TRACE(bpf_testmod_fentry_test2,
+	TP_PROTO(int a, u64 b),
+	TP_ARGS(a, b)
+);
+
 #endif /* _BPF_TESTMOD_EVENTS_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
index 1669a7eeda26..186a25ab429a 100644
--- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
@@ -254,6 +254,22 @@ __bpf_kfunc int *bpf_kfunc_ret_rcu_test_nostruct(int rdonly_buf_size)
 	return NULL;
 }
 
+static struct prog_test_member trusted_ptr;
+
+__bpf_kfunc struct prog_test_member *bpf_kfunc_get_default_trusted_ptr_test(void)
+{
+	return &trusted_ptr;
+}
+
+__bpf_kfunc void bpf_kfunc_put_default_trusted_ptr_test(struct prog_test_member *trusted_ptr)
+{
+	/*
+	 * This BPF kfunc doesn't actually have any put/KF_ACQUIRE
+	 * semantics. We're simply wanting to simulate a BPF kfunc that takes a
+	 * struct prog_test_member pointer as an argument.
+	 */
+}
+
 __bpf_kfunc struct bpf_testmod_ctx *
 bpf_testmod_ctx_create(int *err)
 {
@@ -285,6 +301,12 @@ __bpf_kfunc void bpf_testmod_ctx_release(struct bpf_testmod_ctx *ctx)
 		call_rcu(&ctx->rcu, testmod_free_cb);
 }
 
+__bpf_kfunc void bpf_testmod_ctx_release_dtor(void *ctx)
+{
+	bpf_testmod_ctx_release(ctx);
+}
+CFI_NOSEAL(bpf_testmod_ctx_release_dtor);
+
 static struct bpf_testmod_ops3 *st_ops3;
 
 static int bpf_testmod_test_3(void)
@@ -390,11 +412,15 @@ __weak noinline struct file *bpf_testmod_return_ptr(int arg)
 
 noinline int bpf_testmod_fentry_test1(int a)
 {
+	trace_bpf_testmod_fentry_test1_tp(a);
+
 	return a + 1;
 }
 
 noinline int bpf_testmod_fentry_test2(int a, u64 b)
 {
+	trace_bpf_testmod_fentry_test2_tp(a, b);
+
 	return a + b;
 }
 
@@ -693,9 +719,9 @@ 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_trusted_vma_test)
+BTF_ID_FLAGS(func, bpf_kfunc_trusted_task_test)
+BTF_ID_FLAGS(func, bpf_kfunc_trusted_num_test)
 BTF_ID_FLAGS(func, bpf_kfunc_rcu_task_test, KF_RCU)
 BTF_ID_FLAGS(func, bpf_kfunc_ret_rcu_test, KF_RET_NULL | KF_RCU_PROTECTED)
 BTF_ID_FLAGS(func, bpf_kfunc_ret_rcu_test_nostruct, KF_RET_NULL | KF_RCU_PROTECTED)
@@ -703,11 +729,13 @@ BTF_ID_FLAGS(func, bpf_testmod_ctx_create, KF_ACQUIRE | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_testmod_ctx_release, KF_RELEASE)
 BTF_ID_FLAGS(func, bpf_testmod_ops3_call_test_1)
 BTF_ID_FLAGS(func, bpf_testmod_ops3_call_test_2)
+BTF_ID_FLAGS(func, bpf_kfunc_get_default_trusted_ptr_test);
+BTF_ID_FLAGS(func, bpf_kfunc_put_default_trusted_ptr_test);
 BTF_KFUNCS_END(bpf_testmod_common_kfunc_ids)
 
 BTF_ID_LIST(bpf_testmod_dtor_ids)
 BTF_ID(struct, bpf_testmod_ctx)
-BTF_ID(func, bpf_testmod_ctx_release)
+BTF_ID(func, bpf_testmod_ctx_release_dtor)
 
 static const struct btf_kfunc_id_set bpf_testmod_common_kfunc_set = {
 	.owner = THIS_MODULE,
@@ -1134,6 +1162,38 @@ __bpf_kfunc int bpf_kfunc_st_ops_inc10(struct st_ops_args *args)
 }
 
 __bpf_kfunc int bpf_kfunc_multi_st_ops_test_1(struct st_ops_args *args, u32 id);
+__bpf_kfunc int bpf_kfunc_multi_st_ops_test_1_assoc(struct st_ops_args *args, struct bpf_prog_aux *aux);
+
+__bpf_kfunc int bpf_kfunc_implicit_arg(int a, struct bpf_prog_aux *aux);
+__bpf_kfunc int bpf_kfunc_implicit_arg_legacy(int a, int b, struct bpf_prog_aux *aux);
+__bpf_kfunc int bpf_kfunc_implicit_arg_legacy_impl(int a, int b, struct bpf_prog_aux *aux);
+
+/* hook targets */
+noinline void bpf_testmod_test_hardirq_fn(void) { barrier(); }
+noinline void bpf_testmod_test_softirq_fn(void) { barrier(); }
+
+/* Tasklet for SoftIRQ context */
+static void ctx_check_tasklet_fn(struct tasklet_struct *t)
+{
+	bpf_testmod_test_softirq_fn();
+}
+
+DECLARE_TASKLET(ctx_check_tasklet, ctx_check_tasklet_fn);
+
+/* IRQ Work for HardIRQ context */
+static void ctx_check_irq_fn(struct irq_work *work)
+{
+	bpf_testmod_test_hardirq_fn();
+	tasklet_schedule(&ctx_check_tasklet);
+}
+
+static struct irq_work ctx_check_irq = IRQ_WORK_INIT_HARD(ctx_check_irq_fn);
+
+/* The kfunc trigger */
+__bpf_kfunc void bpf_kfunc_trigger_ctx_check(void)
+{
+	irq_work_queue(&ctx_check_irq);
+}
 
 BTF_KFUNCS_START(bpf_testmod_check_kfunc_ids)
 BTF_ID_FLAGS(func, bpf_testmod_test_mod_kfunc)
@@ -1157,7 +1217,7 @@ BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass2)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail1)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail2)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail3)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_ref, KF_TRUSTED_ARGS | KF_RCU)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_ref, KF_RCU)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_offset)
@@ -1171,11 +1231,16 @@ 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_ID_FLAGS(func, bpf_kfunc_multi_st_ops_test_1, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_prologue, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_epilogue, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_pro_epilogue, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_st_ops_inc10)
+BTF_ID_FLAGS(func, bpf_kfunc_multi_st_ops_test_1)
+BTF_ID_FLAGS(func, bpf_kfunc_multi_st_ops_test_1_assoc, KF_IMPLICIT_ARGS)
+BTF_ID_FLAGS(func, bpf_kfunc_implicit_arg, KF_IMPLICIT_ARGS)
+BTF_ID_FLAGS(func, bpf_kfunc_implicit_arg_legacy, KF_IMPLICIT_ARGS)
+BTF_ID_FLAGS(func, bpf_kfunc_implicit_arg_legacy_impl)
+BTF_ID_FLAGS(func, bpf_kfunc_trigger_ctx_check)
 BTF_KFUNCS_END(bpf_testmod_check_kfunc_ids)
 
 static int bpf_testmod_ops_init(struct btf *btf)
@@ -1637,6 +1702,7 @@ static struct bpf_testmod_multi_st_ops *multi_st_ops_find_nolock(u32 id)
 	return NULL;
 }
 
+/* Call test_1() of the struct_ops map identified by the id */
 int bpf_kfunc_multi_st_ops_test_1(struct st_ops_args *args, u32 id)
 {
 	struct bpf_testmod_multi_st_ops *st_ops;
@@ -1652,6 +1718,38 @@ int bpf_kfunc_multi_st_ops_test_1(struct st_ops_args *args, u32 id)
 	return ret;
 }
 
+/* Call test_1() of the associated struct_ops map */
+int bpf_kfunc_multi_st_ops_test_1_assoc(struct st_ops_args *args, struct bpf_prog_aux *aux)
+{
+	struct bpf_testmod_multi_st_ops *st_ops;
+	int ret = -1;
+
+	st_ops = (struct bpf_testmod_multi_st_ops *)bpf_prog_get_assoc_struct_ops(aux);
+	if (st_ops)
+		ret = st_ops->test_1(args);
+
+	return ret;
+}
+
+int bpf_kfunc_implicit_arg(int a, struct bpf_prog_aux *aux)
+{
+	if (aux && a > 0)
+		return a;
+	return -EINVAL;
+}
+
+int bpf_kfunc_implicit_arg_legacy(int a, int b, struct bpf_prog_aux *aux)
+{
+	if (aux)
+		return a + b;
+	return -EINVAL;
+}
+
+int bpf_kfunc_implicit_arg_legacy_impl(int a, int b, struct bpf_prog_aux *aux)
+{
+	return bpf_kfunc_implicit_arg_legacy(a, b, aux);
+}
+
 static int multi_st_ops_reg(void *kdata, struct bpf_link *link)
 {
 	struct bpf_testmod_multi_st_ops *st_ops =
@@ -1774,6 +1872,10 @@ static void bpf_testmod_exit(void)
 	while (refcount_read(&prog_test_struct.cnt) > 1)
 		msleep(20);
 
+	/* Clean up irqwork and tasklet */
+	irq_work_sync(&ctx_check_irq);
+	tasklet_kill(&ctx_check_tasklet);
+
 	bpf_kfunc_close_sock();
 	sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
 	unregister_bpf_testmod_uprobe();
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h
index 4df6fa6a92cb..d5c5454e257e 100644
--- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h
@@ -161,6 +161,16 @@ void bpf_kfunc_rcu_task_test(struct task_struct *ptr) __ksym;
 struct task_struct *bpf_kfunc_ret_rcu_test(void) __ksym;
 int *bpf_kfunc_ret_rcu_test_nostruct(int rdonly_buf_size) __ksym;
 
-int bpf_kfunc_multi_st_ops_test_1(struct st_ops_args *args, u32 id) __ksym;
+#ifndef __KERNEL__
+extern int bpf_kfunc_multi_st_ops_test_1(struct st_ops_args *args, u32 id) __weak __ksym;
+extern int bpf_kfunc_multi_st_ops_test_1_assoc(struct st_ops_args *args) __weak __ksym;
+#endif
+
+struct prog_test_member *bpf_kfunc_get_default_trusted_ptr_test(void) __ksym;
+void bpf_kfunc_put_default_trusted_ptr_test(struct prog_test_member *trusted_ptr) __ksym;
+
+void bpf_testmod_test_hardirq_fn(void);
+void bpf_testmod_test_softirq_fn(void);
+void bpf_kfunc_trigger_ctx_check(void) __ksym;
 
 #endif /* _BPF_TESTMOD_KFUNC_H */
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index 9437bdd4afa5..a5576b2dfc26 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -4,6 +4,18 @@
 
 #include <bpf/libbpf.h>
 
+#ifdef __x86_64__
+#define SYS_PREFIX "__x64_"
+#elif defined(__s390x__)
+#define SYS_PREFIX "__s390x_"
+#elif defined(__aarch64__)
+#define SYS_PREFIX "__arm64_"
+#elif defined(__riscv)
+#define SYS_PREFIX "__riscv_"
+#else
+#define SYS_PREFIX ""
+#endif
+
 #define __ALIGN_MASK(x, mask)	(((x)+(mask))&~(mask))
 #define ALIGN(x, a)		__ALIGN_MASK(x, (typeof(x))(a)-1)
 
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index c8d640802cce..9ca83dce100d 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -220,7 +220,7 @@
 	},
 	.result_unpriv = REJECT,
 	.result = REJECT,
-	.errstr = "variable ptr_ access var_off=(0x0; 0x7) disallowed",
+	.errstr = "variable trusted_ptr_ access var_off=(0x0; 0x7) disallowed",
 },
 {
 	"calls: invalid kfunc call: referenced arg needs refcounted PTR_TO_BTF_ID",
diff --git a/tools/testing/selftests/bpf/verifier/direct_value_access.c b/tools/testing/selftests/bpf/verifier/direct_value_access.c
index c0648dc009b5..e569d119fb60 100644
--- a/tools/testing/selftests/bpf/verifier/direct_value_access.c
+++ b/tools/testing/selftests/bpf/verifier/direct_value_access.c
@@ -81,7 +81,7 @@
 	},
 	.fixup_map_array_48b = { 1 },
 	.result = REJECT,
-	.errstr = "direct value offset of 4294967295 is not allowed",
+	.errstr = "invalid access to map value pointer, value_size=48 off=4294967295",
 },
 {
 	"direct map access, write test 8",
@@ -141,7 +141,7 @@
 	},
 	.fixup_map_array_48b = { 1 },
 	.result = REJECT,
-	.errstr = "direct value offset of 536870912 is not allowed",
+	.errstr = "invalid access to map value pointer, value_size=48 off=536870912",
 },
 {
 	"direct map access, write test 13",
diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c
index 59a020c35647..061d98f6e9bb 100644
--- a/tools/testing/selftests/bpf/verifier/precise.c
+++ b/tools/testing/selftests/bpf/verifier/precise.c
@@ -229,11 +229,11 @@
 {
 	"precise: program doesn't prematurely prune branches",
 	.insns = {
-		BPF_ALU64_IMM(BPF_MOV, BPF_REG_6, 0x400),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+		BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_0),
 		BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0),
 		BPF_ALU64_IMM(BPF_MOV, BPF_REG_8, 0),
 		BPF_ALU64_IMM(BPF_MOV, BPF_REG_9, 0x80000000),
-		BPF_ALU64_IMM(BPF_MOD, BPF_REG_6, 0x401),
 		BPF_JMP_IMM(BPF_JA, 0, 0, 0),
 		BPF_JMP_REG(BPF_JLE, BPF_REG_6, BPF_REG_9, 2),
 		BPF_ALU64_IMM(BPF_MOD, BPF_REG_6, 1),
diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c
index e962f133250c..1be1e353d40a 100644
--- a/tools/testing/selftests/bpf/veristat.c
+++ b/tools/testing/selftests/bpf/veristat.c
@@ -2580,7 +2580,7 @@ static void output_stats(const struct verif_stats *s, enum resfmt fmt, bool last
 	if (last && fmt == RESFMT_TABLE) {
 		output_header_underlines();
 		printf("Done. Processed %d files, %d programs. Skipped %d files, %d programs.\n",
-		       env.files_processed, env.files_skipped, env.progs_processed, env.progs_skipped);
+		       env.files_processed, env.progs_processed, env.files_skipped, env.progs_skipped);
 	}
 }
 
diff --git a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h
index 531228b849da..80ab60905865 100644
--- a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h
+++ b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h
@@ -116,10 +116,8 @@ extern int hid_bpf_try_input_report(struct hid_bpf_ctx *ctx,
 /* bpf_wq implementation */
 extern int bpf_wq_init(struct bpf_wq *wq, void *p__map, unsigned int flags) __weak __ksym;
 extern int bpf_wq_start(struct bpf_wq *wq, unsigned int flags) __weak __ksym;
-extern int bpf_wq_set_callback_impl(struct bpf_wq *wq,
-		int (callback_fn)(void *map, int *key, void *wq),
-		unsigned int flags__k, void *aux__ign) __weak __ksym;
-#define bpf_wq_set_callback(timer, cb, flags) \
-	bpf_wq_set_callback_impl(timer, cb, flags, NULL)
+extern int bpf_wq_set_callback(struct bpf_wq *wq,
+		int (*callback_fn)(void *, int *, void *),
+		unsigned int flags) __weak __ksym;
 
 #endif /* __HID_BPF_HELPERS_H */