diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst
index 0d2647fb358d7ce1a4a85bd994d9b05e8ea0cec9..723408e399abd8ce83c8d9bc2c40dcf251c258b9 100644
--- a/Documentation/bpf/kfuncs.rst
+++ b/Documentation/bpf/kfuncs.rst
@@ -37,16 +37,14 @@ prototype in a header for the wrapper kfunc.
 An example is given below::
 
         /* Disables missing prototype warnings */
-        __diag_push();
-        __diag_ignore_all("-Wmissing-prototypes",
-                          "Global kfuncs as their definitions will be in BTF");
+        __bpf_kfunc_start_defs();
 
         __bpf_kfunc struct task_struct *bpf_find_get_task_by_vpid(pid_t nr)
         {
                 return find_get_task_by_vpid(nr);
         }
 
-        __diag_pop();
+        __bpf_kfunc_end_defs();
 
 A wrapper kfunc is often needed when we need to annotate parameters of the
 kfunc. Otherwise one may directly make the kfunc visible to the BPF program by
diff --git a/include/linux/btf.h b/include/linux/btf.h
index c2231c64d60b92a7f7e4ea52e479cbdbf2611693..59d404e22814e885ae8429a361f2f43bed3b8f30 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -84,6 +84,17 @@
  */
 #define __bpf_kfunc __used noinline
 
+#define __bpf_kfunc_start_defs()					       \
+	__diag_push();							       \
+	__diag_ignore_all("-Wmissing-declarations",			       \
+			  "Global kfuncs as their definitions will be in BTF");\
+	__diag_ignore_all("-Wmissing-prototypes",			       \
+			  "Global kfuncs as their definitions will be in BTF")
+
+#define __bpf_kfunc_end_defs() __diag_pop()
+#define __bpf_hook_start() __bpf_kfunc_start_defs()
+#define __bpf_hook_end() __bpf_kfunc_end_defs()
+
 /*
  * Return the name of the passed struct, if exists, or halt the build if for
  * example the structure gets renamed. In this way, developers have to revisit
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 833faa04461bc201f6e1d154f5444a274e582812..0fae79164187094d77def3bdc9cd6e6cac99c733 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -782,9 +782,7 @@ struct bpf_iter_num_kern {
 	int end; /* final value, exclusive */
 } __aligned(8);
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end)
 {
@@ -843,4 +841,4 @@ __bpf_kfunc void bpf_iter_num_destroy(struct bpf_iter_num *it)
 	s->cur = s->end = 0;
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c
index 209e5135f9fbc58321477e8191010cadf0f3e060..f04a468cf6a72688121ced9e4ddcf0555b7758c5 100644
--- a/kernel/bpf/cgroup_iter.c
+++ b/kernel/bpf/cgroup_iter.c
@@ -282,7 +282,7 @@ static struct bpf_iter_reg bpf_cgroup_reg_info = {
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__cgroup, cgroup),
-		  PTR_TO_BTF_ID_OR_NULL },
+		  PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
 	},
 	.seq_info		= &cgroup_iter_seq_info,
 };
@@ -305,9 +305,7 @@ struct bpf_iter_css_kern {
 	unsigned int flags;
 } __attribute__((aligned(8)));
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		"Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc int bpf_iter_css_new(struct bpf_iter_css *it,
 		struct cgroup_subsys_state *start, unsigned int flags)
@@ -358,4 +356,4 @@ __bpf_kfunc void bpf_iter_css_destroy(struct bpf_iter_css *it)
 {
 }
 
-__diag_pop();
\ No newline at end of file
+__bpf_kfunc_end_defs();
diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c
index 6983af8e093c4b0260f64d62d7c5d040e67e647f..e01c741e54e7b8dcf7ebb60b65955fafc55639c8 100644
--- a/kernel/bpf/cpumask.c
+++ b/kernel/bpf/cpumask.c
@@ -34,9 +34,7 @@ static bool cpu_valid(u32 cpu)
 	return cpu < nr_cpu_ids;
 }
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global kfuncs as their definitions will be in BTF");
+__bpf_kfunc_start_defs();
 
 /**
  * bpf_cpumask_create() - Create a mutable BPF cpumask.
@@ -407,7 +405,7 @@ __bpf_kfunc u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1,
 	return cpumask_any_and_distribute(src1, src2);
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(cpumask_kfunc_btf_ids)
 BTF_ID_FLAGS(func, bpf_cpumask_create, KF_ACQUIRE | KF_RET_NULL)
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index e46ac288a1080b42feae40628d8e852fd980c7d7..56b0c1f678ee754101233daec601f4f62623e0ef 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1177,13 +1177,6 @@ BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map
 		ret = -EBUSY;
 		goto out;
 	}
-	if (!atomic64_read(&map->usercnt)) {
-		/* maps with timers must be either held by user space
-		 * or pinned in bpffs.
-		 */
-		ret = -EPERM;
-		goto out;
-	}
 	/* allocate hrtimer via map_kmalloc to use memcg accounting */
 	t = bpf_map_kmalloc_node(map, sizeof(*t), GFP_ATOMIC, map->numa_node);
 	if (!t) {
@@ -1196,7 +1189,21 @@ BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map
 	rcu_assign_pointer(t->callback_fn, NULL);
 	hrtimer_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT);
 	t->timer.function = bpf_timer_cb;
-	timer->timer = t;
+	WRITE_ONCE(timer->timer, t);
+	/* Guarantee the order between timer->timer and map->usercnt. So
+	 * when there are concurrent uref release and bpf timer init, either
+	 * bpf_timer_cancel_and_free() called by uref release reads a no-NULL
+	 * timer or atomic64_read() below returns a zero usercnt.
+	 */
+	smp_mb();
+	if (!atomic64_read(&map->usercnt)) {
+		/* maps with timers must be either held by user space
+		 * or pinned in bpffs.
+		 */
+		WRITE_ONCE(timer->timer, NULL);
+		kfree(t);
+		ret = -EPERM;
+	}
 out:
 	__bpf_spin_unlock_irqrestore(&timer->lock);
 	return ret;
@@ -1374,7 +1381,7 @@ void bpf_timer_cancel_and_free(void *val)
 	/* The subsequent bpf_timer_start/cancel() helpers won't be able to use
 	 * this timer, since it won't be initialized.
 	 */
-	timer->timer = NULL;
+	WRITE_ONCE(timer->timer, NULL);
 out:
 	__bpf_spin_unlock_irqrestore(&timer->lock);
 	if (!t)
@@ -1886,9 +1893,7 @@ void bpf_rb_root_free(const struct btf_field *field, void *rb_root,
 	}
 }
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign)
 {
@@ -2505,7 +2510,7 @@ __bpf_kfunc void bpf_throw(u64 cookie)
 	WARN(1, "A call to BPF exception callback should never return\n");
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(generic_btf_ids)
 #ifdef CONFIG_KEXEC_CORE
@@ -2564,15 +2569,17 @@ BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_iter_task_vma_new, KF_ITER_NEW | KF_RCU)
 BTF_ID_FLAGS(func, bpf_iter_task_vma_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY)
+#ifdef CONFIG_CGROUPS
 BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
 BTF_ID_FLAGS(func, bpf_iter_css_task_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY)
-BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
-BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL)
-BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_iter_css_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
 BTF_ID_FLAGS(func, bpf_iter_css_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_css_destroy, KF_ITER_DESTROY)
+#endif
+BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
+BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_dynptr_adjust)
 BTF_ID_FLAGS(func, bpf_dynptr_is_null)
 BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly)
diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index 6fc9dae9edc81cad457b3e193ce671a3b0723aa8..6abd7c5df4b39e4e956258e67c4dbe6b8dd8edeb 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -193,9 +193,7 @@ static int __init bpf_map_iter_init(void)
 
 late_initcall(bpf_map_iter_init);
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc s64 bpf_map_sum_elem_count(const struct bpf_map *map)
 {
@@ -213,7 +211,7 @@ __bpf_kfunc s64 bpf_map_sum_elem_count(const struct bpf_map *map)
 	return ret;
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(bpf_map_iter_kfunc_ids)
 BTF_ID_FLAGS(func, bpf_map_sum_elem_count, KF_TRUSTED_ARGS)
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 654601dd6b493d44111f3fefb16c0b412d69ebe2..26082b97894d3c0d64f4c909122ec3820f73f197 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -704,7 +704,7 @@ static struct bpf_iter_reg task_reg_info = {
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__task, task),
-		  PTR_TO_BTF_ID_OR_NULL },
+		  PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
 	},
 	.seq_info		= &task_seq_info,
 	.fill_link_info		= bpf_iter_fill_link_info,
@@ -822,9 +822,7 @@ struct bpf_iter_task_vma_kern {
 	struct bpf_iter_task_vma_kern_data *data;
 } __attribute__((aligned(8)));
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it,
 				      struct task_struct *task, u64 addr)
@@ -890,7 +888,9 @@ __bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it)
 	}
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
+
+#ifdef CONFIG_CGROUPS
 
 struct bpf_iter_css_task {
 	__u64 __opaque[1];
@@ -900,9 +900,7 @@ struct bpf_iter_css_task_kern {
 	struct css_task_iter *css_it;
 } __attribute__((aligned(8)));
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc int bpf_iter_css_task_new(struct bpf_iter_css_task *it,
 		struct cgroup_subsys_state *css, unsigned int flags)
@@ -948,7 +946,9 @@ __bpf_kfunc void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it)
 	bpf_mem_free(&bpf_global_ma, kit->css_it);
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
+
+#endif /* CONFIG_CGROUPS */
 
 struct bpf_iter_task {
 	__u64 __opaque[3];
@@ -969,9 +969,7 @@ enum {
 	BPF_TASK_ITER_PROC_THREADS
 };
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it,
 		struct task_struct *task__nullable, unsigned int flags)
@@ -1041,7 +1039,7 @@ __bpf_kfunc void bpf_iter_task_destroy(struct bpf_iter_task *it)
 {
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 857d76694517121e8f6e34f7f7c0c4429720b6a6..bd1c42eb540f1f7565d1d0c10457884c10f7a37a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3742,7 +3742,12 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 	if (class == BPF_ALU || class == BPF_ALU64) {
 		if (!bt_is_reg_set(bt, dreg))
 			return 0;
-		if (opcode == BPF_MOV) {
+		if (opcode == BPF_END || opcode == BPF_NEG) {
+			/* sreg is reserved and unused
+			 * dreg still need precision before this insn
+			 */
+			return 0;
+		} else if (opcode == BPF_MOV) {
 			if (BPF_SRC(insn->code) == BPF_X) {
 				/* dreg = sreg or dreg = (s8, s16, s32)sreg
 				 * dreg needs precision after this insn
@@ -4674,7 +4679,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 		   insn->imm != 0 && env->bpf_capable) {
 		struct bpf_reg_state fake_reg = {};
 
-		__mark_reg_known(&fake_reg, (u32)insn->imm);
+		__mark_reg_known(&fake_reg, insn->imm);
 		fake_reg.type = SCALAR_VALUE;
 		save_register_state(state, spi, &fake_reg, size);
 	} else if (reg && is_spillable_regtype(reg->type)) {
@@ -5388,7 +5393,9 @@ static bool in_rcu_cs(struct bpf_verifier_env *env)
 /* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */
 BTF_SET_START(rcu_protected_types)
 BTF_ID(struct, prog_test_ref_kfunc)
+#ifdef CONFIG_CGROUPS
 BTF_ID(struct, cgroup)
+#endif
 BTF_ID(struct, bpf_cpumask)
 BTF_ID(struct, task_struct)
 BTF_SET_END(rcu_protected_types)
@@ -10835,7 +10842,9 @@ BTF_ID(func, bpf_dynptr_clone)
 BTF_ID(func, bpf_percpu_obj_new_impl)
 BTF_ID(func, bpf_percpu_obj_drop_impl)
 BTF_ID(func, bpf_throw)
+#ifdef CONFIG_CGROUPS
 BTF_ID(func, bpf_iter_css_task_new)
+#endif
 BTF_SET_END(special_kfunc_set)
 
 BTF_ID_LIST(special_kfunc_list)
@@ -10861,7 +10870,11 @@ BTF_ID(func, bpf_dynptr_clone)
 BTF_ID(func, bpf_percpu_obj_new_impl)
 BTF_ID(func, bpf_percpu_obj_drop_impl)
 BTF_ID(func, bpf_throw)
+#ifdef CONFIG_CGROUPS
 BTF_ID(func, bpf_iter_css_task_new)
+#else
+BTF_ID_UNUSED
+#endif
 
 static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta)
 {
@@ -11394,6 +11407,12 @@ static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env,
 						  &meta->arg_rbtree_root.field);
 }
 
+/*
+ * css_task iter allowlist is needed to avoid dead locking on css_set_lock.
+ * LSM hooks and iters (both sleepable and non-sleepable) are safe.
+ * Any sleepable progs are also safe since bpf_check_attach_target() enforce
+ * them can only be attached to some specific hook points.
+ */
 static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env)
 {
 	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
@@ -11401,10 +11420,12 @@ static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env)
 	switch (prog_type) {
 	case BPF_PROG_TYPE_LSM:
 		return true;
-	case BPF_TRACE_ITER:
-		return env->prog->aux->sleepable;
+	case BPF_PROG_TYPE_TRACING:
+		if (env->prog->expected_attach_type == BPF_TRACE_ITER)
+			return true;
+		fallthrough;
 	default:
-		return false;
+		return env->prog->aux->sleepable;
 	}
 }
 
@@ -11663,7 +11684,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 		case KF_ARG_PTR_TO_ITER:
 			if (meta->func_id == special_kfunc_list[KF_bpf_iter_css_task_new]) {
 				if (!check_css_task_iter_allowlist(env)) {
-					verbose(env, "css_task_iter is only allowed in bpf_lsm and bpf iter-s\n");
+					verbose(env, "css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs\n");
 					return -EINVAL;
 				}
 			}
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index d80d7a6081412994582e2a3686442226b582cd50..c0adb7254b45aef82756c523cee94651e0dc81c6 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -156,19 +156,16 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
  * optimize away the callsite. Therefore, __weak is needed to ensure that the
  * call is still emitted, by telling the compiler that we don't know what the
  * function might eventually be.
- *
- * __diag_* below are needed to dismiss the missing prototype warning.
  */
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "kfuncs which will be used in BPF programs");
+
+__bpf_hook_start();
 
 __weak noinline void bpf_rstat_flush(struct cgroup *cgrp,
 				     struct cgroup *parent, int cpu)
 {
 }
 
-__diag_pop();
+__bpf_hook_end();
 
 /* see cgroup_rstat_flush() */
 static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index df697c74d5197a21a49691cced48138397851076..84e8a0f6e4e0b0283eb6d7d6b72e5c0e2761c8c6 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1252,9 +1252,7 @@ static const struct bpf_func_proto bpf_get_func_arg_cnt_proto = {
 };
 
 #ifdef CONFIG_KEYS
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "kfuncs which will be used in BPF programs");
+__bpf_kfunc_start_defs();
 
 /**
  * bpf_lookup_user_key - lookup a key by its serial
@@ -1404,7 +1402,7 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr,
 }
 #endif /* CONFIG_SYSTEM_DATA_VERIFICATION */
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(key_sig_kfunc_set)
 BTF_ID_FLAGS(func, bpf_lookup_user_key, KF_ACQUIRE | KF_RET_NULL | KF_SLEEPABLE)
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 0841f8d824198d0409d68aa178f2fba4d8ebb11d..c9fdcc5cdce10d8d9f5ed93cfb22d6d9e4bdd25d 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -503,9 +503,8 @@ static int bpf_test_finish(const union bpf_attr *kattr,
  * architecture dependent calling conventions. 7+ can be supported in the
  * future.
  */
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
+
 __bpf_kfunc int bpf_fentry_test1(int a)
 {
 	return a + 1;
@@ -605,7 +604,7 @@ __bpf_kfunc void bpf_kfunc_call_memb_release(struct prog_test_member *p)
 {
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(bpf_test_modify_return_ids)
 BTF_ID_FLAGS(func, bpf_modify_return_test)
diff --git a/net/core/filter.c b/net/core/filter.c
index 21d75108c2e94be490af74672a4845c4cb945ce8..383f96b0a1c78026629ef4e6b8c172019d29d35c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -11767,9 +11767,7 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id)
 	return func;
 }
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 __bpf_kfunc int bpf_dynptr_from_skb(struct sk_buff *skb, u64 flags,
 				    struct bpf_dynptr_kern *ptr__uninit)
 {
@@ -11816,7 +11814,7 @@ __bpf_kfunc int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern,
 
 	return 0;
 }
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
 			       struct bpf_dynptr_kern *ptr__uninit)
@@ -11879,10 +11877,7 @@ static int __init bpf_kfunc_init(void)
 }
 late_initcall(bpf_kfunc_init);
 
-/* Disables missing prototype warnings */
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 /* bpf_sock_destroy: Destroy the given socket with ECONNABORTED error code.
  *
@@ -11916,7 +11911,7 @@ __bpf_kfunc int bpf_sock_destroy(struct sock_common *sock)
 	return sk->sk_prot->diag_destroy(sk, ECONNABORTED);
 }
 
-__diag_pop()
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(bpf_sk_iter_kfunc_ids)
 BTF_ID_FLAGS(func, bpf_sock_destroy, KF_TRUSTED_ARGS)
diff --git a/net/core/xdp.c b/net/core/xdp.c
index df4789ab512d72581915d2a829369a05398434bd..b6f1d6dab3f2e3c2e8515ad1293fb284cfc42218 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -696,9 +696,7 @@ struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf)
 	return nxdpf;
 }
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 /**
  * bpf_xdp_metadata_rx_timestamp - Read XDP frame RX timestamp.
@@ -738,7 +736,7 @@ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash,
 	return -EOPNOTSUPP;
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(xdp_metadata_kfunc_ids)
 #define XDP_METADATA_KFUNC(_, __, name, ___) BTF_ID_FLAGS(func, name, KF_TRUSTED_ARGS)
diff --git a/net/ipv4/fou_bpf.c b/net/ipv4/fou_bpf.c
index 3760a14b6b576b07c60879bf58831c382cd103bc..4da03bf45c9b753f957d4c561d2075c825f07791 100644
--- a/net/ipv4/fou_bpf.c
+++ b/net/ipv4/fou_bpf.c
@@ -22,9 +22,7 @@ enum bpf_fou_encap_type {
 	FOU_BPF_ENCAP_GUE,
 };
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in BTF");
+__bpf_kfunc_start_defs();
 
 /* bpf_skb_set_fou_encap - Set FOU encap parameters
  *
@@ -100,7 +98,7 @@ __bpf_kfunc int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx,
 	return 0;
 }
 
-__diag_pop()
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(fou_kfunc_set)
 BTF_ID_FLAGS(func, bpf_skb_set_fou_encap)
diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c
index b21799d468d2815413cc1334cb6c5e5df7fe231d..475358ec821296c6b3fc771e96ba4d00b8da78f1 100644
--- a/net/netfilter/nf_conntrack_bpf.c
+++ b/net/netfilter/nf_conntrack_bpf.c
@@ -230,9 +230,7 @@ static int _nf_conntrack_btf_struct_access(struct bpf_verifier_log *log,
 	return 0;
 }
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in nf_conntrack BTF");
+__bpf_kfunc_start_defs();
 
 /* bpf_xdp_ct_alloc - Allocate a new CT entry
  *
@@ -467,7 +465,7 @@ __bpf_kfunc int bpf_ct_change_status(struct nf_conn *nfct, u32 status)
 	return nf_ct_change_status_common(nfct, status);
 }
 
-__diag_pop()
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(nf_ct_kfunc_set)
 BTF_ID_FLAGS(func, bpf_xdp_ct_alloc, KF_ACQUIRE | KF_RET_NULL)
diff --git a/net/netfilter/nf_nat_bpf.c b/net/netfilter/nf_nat_bpf.c
index 141ee7783223dad0e8511565c233873223c3e2e2..6e3b2f58855fc05d31842a6ebd836d72344ef031 100644
--- a/net/netfilter/nf_nat_bpf.c
+++ b/net/netfilter/nf_nat_bpf.c
@@ -12,9 +12,7 @@
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_nat.h>
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in nf_nat BTF");
+__bpf_kfunc_start_defs();
 
 /* bpf_ct_set_nat_info - Set source or destination nat address
  *
@@ -54,7 +52,7 @@ __bpf_kfunc int bpf_ct_set_nat_info(struct nf_conn___init *nfct,
 	return nf_nat_setup_info(ct, &range, manip) == NF_DROP ? -ENOMEM : 0;
 }
 
-__diag_pop()
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(nf_nat_kfunc_set)
 BTF_ID_FLAGS(func, bpf_ct_set_nat_info, KF_TRUSTED_ARGS)
diff --git a/net/socket.c b/net/socket.c
index 0d1c4e78fc7f8c7fde79cb57a6c98a12487b24cc..3379c64217a4c1e166f3fc0ef5053c152b2eb80e 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1685,20 +1685,16 @@ struct file *__sys_socket_file(int family, int type, int protocol)
  *	Therefore, __weak is needed to ensure that the call is still
  *	emitted, by telling the compiler that we don't know what the
  *	function might eventually be.
- *
- *	__diag_* below are needed to dismiss the missing prototype warning.
  */
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "A fmod_ret entry point for BPF programs");
+__bpf_hook_start();
 
 __weak noinline int update_socket_protocol(int family, int type, int protocol)
 {
 	return protocol;
 }
 
-__diag_pop();
+__bpf_hook_end();
 
 int __sys_socket(int family, int type, int protocol)
 {
diff --git a/net/xfrm/xfrm_interface_bpf.c b/net/xfrm/xfrm_interface_bpf.c
index d74f3fd20f2bf25f0166b293fc378823b2612e8b..7d5e920141e9b71c0f020f7b4c7700fb8aa07eda 100644
--- a/net/xfrm/xfrm_interface_bpf.c
+++ b/net/xfrm/xfrm_interface_bpf.c
@@ -27,9 +27,7 @@ struct bpf_xfrm_info {
 	int link;
 };
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in xfrm_interface BTF");
+__bpf_kfunc_start_defs();
 
 /* bpf_skb_get_xfrm_info - Get XFRM metadata
  *
@@ -93,7 +91,7 @@ __bpf_kfunc int bpf_skb_set_xfrm_info(struct __sk_buff *skb_ctx, const struct bp
 	return 0;
 }
 
-__diag_pop()
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(xfrm_ifc_kfunc_set)
 BTF_ID_FLAGS(func, bpf_skb_get_xfrm_info)
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index a5e246f7b202748b142e0b53b6b21c6f3fe220e5..91907b321f913408ba4ecd31cf679ea07f672e4e 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -39,9 +39,7 @@ struct bpf_testmod_struct_arg_4 {
 	int b;
 };
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in bpf_testmod.ko BTF");
+__bpf_hook_start();
 
 noinline int
 bpf_testmod_test_struct_arg_1(struct bpf_testmod_struct_arg_2 a, int b, int c) {
@@ -335,7 +333,7 @@ noinline int bpf_fentry_shadow_test(int a)
 }
 EXPORT_SYMBOL_GPL(bpf_fentry_shadow_test);
 
-__diag_pop();
+__bpf_hook_end();
 
 static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = {
 	.attr = { .name = "bpf_testmod", .mode = 0666, },
diff --git a/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
index 1a9eeefda9a8701f967d727813d46db3e8f79850..8bf497a9843e1b97d0e23cd80e82c5787e45c981 100644
--- a/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
+++ b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
@@ -326,20 +326,14 @@ static int map_create(__u32 type, const char *name, struct bpf_map_create_opts *
 
 static int create_hash(void)
 {
-	struct bpf_map_create_opts map_opts = {
-		.sz = sizeof(map_opts),
-		.map_flags = BPF_F_NO_PREALLOC,
-	};
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts, .map_flags = BPF_F_NO_PREALLOC);
 
 	return map_create(BPF_MAP_TYPE_HASH, "hash", &map_opts);
 }
 
 static int create_percpu_hash(void)
 {
-	struct bpf_map_create_opts map_opts = {
-		.sz = sizeof(map_opts),
-		.map_flags = BPF_F_NO_PREALLOC,
-	};
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts, .map_flags = BPF_F_NO_PREALLOC);
 
 	return map_create(BPF_MAP_TYPE_PERCPU_HASH, "percpu_hash", &map_opts);
 }
@@ -356,21 +350,17 @@ static int create_percpu_hash_prealloc(void)
 
 static int create_lru_hash(__u32 type, __u32 map_flags)
 {
-	struct bpf_map_create_opts map_opts = {
-		.sz = sizeof(map_opts),
-		.map_flags = map_flags,
-	};
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts, .map_flags = map_flags);
 
 	return map_create(type, "lru_hash", &map_opts);
 }
 
 static int create_hash_of_maps(void)
 {
-	struct bpf_map_create_opts map_opts = {
-		.sz = sizeof(map_opts),
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts,
 		.map_flags = BPF_F_NO_PREALLOC,
 		.inner_map_fd = create_small_hash(),
-	};
+	);
 	int ret;
 
 	ret = map_create_opts(BPF_MAP_TYPE_HASH_OF_MAPS, "hash_of_maps",
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c b/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c
index e02feb5fae97dd814775c0149893b4507cef2332..574d9a0cdc8e4a33c730bcb11a4136d60f718e86 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c
@@ -4,6 +4,7 @@
 #include <test_progs.h>
 #include <bpf/libbpf.h>
 #include <bpf/btf.h>
+#include "iters_css_task.skel.h"
 #include "cgroup_iter.skel.h"
 #include "cgroup_helpers.h"
 
@@ -263,6 +264,35 @@ static void test_walk_dead_self_only(struct cgroup_iter *skel)
 	close(cgrp_fd);
 }
 
+static void test_walk_self_only_css_task(void)
+{
+	struct iters_css_task *skel;
+	int err;
+
+	skel = iters_css_task__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	bpf_program__set_autoload(skel->progs.cgroup_id_printer, true);
+
+	err = iters_css_task__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	err = join_cgroup(cg_path[CHILD2]);
+	if (!ASSERT_OK(err, "join_cgroup"))
+		goto cleanup;
+
+	skel->bss->target_pid = getpid();
+	snprintf(expected_output, sizeof(expected_output),
+		PROLOGUE "%8llu\n" EPILOGUE, cg_id[CHILD2]);
+	read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[CHILD2],
+		BPF_CGROUP_ITER_SELF_ONLY, "test_walk_self_only_css_task");
+	ASSERT_EQ(skel->bss->css_task_cnt, 1, "css_task_cnt");
+cleanup:
+	iters_css_task__destroy(skel);
+}
+
 void test_cgroup_iter(void)
 {
 	struct cgroup_iter *skel = NULL;
@@ -293,6 +323,9 @@ void test_cgroup_iter(void)
 		test_walk_self_only(skel);
 	if (test__start_subtest("cgroup_iter__dead_self_only"))
 		test_walk_dead_self_only(skel);
+	if (test__start_subtest("cgroup_iter__self_only_css_task"))
+		test_walk_self_only_css_task();
+
 out:
 	cgroup_iter__destroy(skel);
 	cleanup_cgroups();
diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c
index c2425791c9232f96b9430ef59058b88ee5cece7a..bf84d4a1d9ae2c68ceeac9f25373fd9df01b6935 100644
--- a/tools/testing/selftests/bpf/prog_tests/iters.c
+++ b/tools/testing/selftests/bpf/prog_tests/iters.c
@@ -294,6 +294,7 @@ void test_iters(void)
 	RUN_TESTS(iters_state_safety);
 	RUN_TESTS(iters_looping);
 	RUN_TESTS(iters);
+	RUN_TESTS(iters_css_task);
 
 	if (env.has_testmod)
 		RUN_TESTS(iters_testmod_seq);
diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpffs.c b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c
index 214d9f4a94a538c2675337671ccaf92ef1012d8d..ea933fd151c389f11ba1559a397d5cbfe2c4583c 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_bpffs.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c
@@ -8,7 +8,8 @@
 #include <sys/types.h>
 #include <test_progs.h>
 
-#define TDIR "/sys/kernel/debug"
+/* TDIR must be in a location we can create a directory in. */
+#define TDIR "/tmp/test_bpffs_testdir"
 
 static int read_iter(char *file)
 {
@@ -43,8 +44,11 @@ static int fn(void)
 	if (!ASSERT_OK(err, "mount /"))
 		goto out;
 
-	err = umount(TDIR);
-	if (!ASSERT_OK(err, "umount " TDIR))
+	err =  mkdir(TDIR, 0777);
+	/* If the directory already exists we can carry on. It may be left over
+	 * from a previous run.
+	 */
+	if ((err && errno != EEXIST) && !ASSERT_OK(err, "mkdir " TDIR))
 		goto out;
 
 	err = mount("none", TDIR, "tmpfs", 0, NULL);
@@ -138,6 +142,7 @@ static int fn(void)
 	rmdir(TDIR "/fs1");
 	rmdir(TDIR "/fs2");
 	umount(TDIR);
+	rmdir(TDIR);
 	exit(err);
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index e3e68c97b40cfdff5f0a2de0dac8e30cfa2cf0c0..e5c61aa6604ace3fb1b70c22d353a065a4c9162d 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -46,6 +46,7 @@
 #include "verifier_movsx.skel.h"
 #include "verifier_netfilter_ctx.skel.h"
 #include "verifier_netfilter_retcode.skel.h"
+#include "verifier_precision.skel.h"
 #include "verifier_prevent_map_lookup.skel.h"
 #include "verifier_raw_stack.skel.h"
 #include "verifier_raw_tp_writable.skel.h"
@@ -153,6 +154,7 @@ void test_verifier_meta_access(void)          { RUN(verifier_meta_access); }
 void test_verifier_movsx(void)                 { RUN(verifier_movsx); }
 void test_verifier_netfilter_ctx(void)        { RUN(verifier_netfilter_ctx); }
 void test_verifier_netfilter_retcode(void)    { RUN(verifier_netfilter_retcode); }
+void test_verifier_precision(void)            { RUN(verifier_precision); }
 void test_verifier_prevent_map_lookup(void)   { RUN(verifier_prevent_map_lookup); }
 void test_verifier_raw_stack(void)            { RUN(verifier_raw_stack); }
 void test_verifier_raw_tp_writable(void)      { RUN(verifier_raw_tp_writable); }
diff --git a/tools/testing/selftests/bpf/progs/iters_css_task.c b/tools/testing/selftests/bpf/progs/iters_css_task.c
index 5089ce384a1c7afa593ef273eaed8b043770e24e..9ac758649cb8ccd0af666a865ea314c9e7fa5819 100644
--- a/tools/testing/selftests/bpf/progs/iters_css_task.c
+++ b/tools/testing/selftests/bpf/progs/iters_css_task.c
@@ -10,6 +10,7 @@
 
 char _license[] SEC("license") = "GPL";
 
+struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
 struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
 void bpf_cgroup_release(struct cgroup *p) __ksym;
 
@@ -45,3 +46,57 @@ int BPF_PROG(iter_css_task_for_each, struct vm_area_struct *vma,
 
 	return -EPERM;
 }
+
+static inline u64 cgroup_id(struct cgroup *cgrp)
+{
+	return cgrp->kn->id;
+}
+
+SEC("?iter/cgroup")
+int cgroup_id_printer(struct bpf_iter__cgroup *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct cgroup *cgrp = ctx->cgroup;
+	struct cgroup_subsys_state *css;
+	struct task_struct *task;
+
+	/* epilogue */
+	if (cgrp == NULL) {
+		BPF_SEQ_PRINTF(seq, "epilogue\n");
+		return 0;
+	}
+
+	/* prologue */
+	if (ctx->meta->seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "prologue\n");
+
+	BPF_SEQ_PRINTF(seq, "%8llu\n", cgroup_id(cgrp));
+
+	css = &cgrp->self;
+	css_task_cnt = 0;
+	bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) {
+		if (task->pid == target_pid)
+			css_task_cnt++;
+	}
+
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int BPF_PROG(iter_css_task_for_each_sleep)
+{
+	u64 cgrp_id = bpf_get_current_cgroup_id();
+	struct cgroup *cgrp = bpf_cgroup_from_id(cgrp_id);
+	struct cgroup_subsys_state *css;
+	struct task_struct *task;
+
+	if (cgrp == NULL)
+		return 0;
+	css = &cgrp->self;
+
+	bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) {
+
+	}
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/iters_task_failure.c b/tools/testing/selftests/bpf/progs/iters_task_failure.c
index c3bf96a67dba9d11fcd5ee0119a88568315bb133..6b1588d706527321f15cfa2dae9e900bd4393bea 100644
--- a/tools/testing/selftests/bpf/progs/iters_task_failure.c
+++ b/tools/testing/selftests/bpf/progs/iters_task_failure.c
@@ -84,8 +84,8 @@ int BPF_PROG(iter_css_lock_and_unlock)
 	return 0;
 }
 
-SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
-__failure __msg("css_task_iter is only allowed in bpf_lsm and bpf iter-s")
+SEC("?fentry/" SYS_PREFIX "sys_getpgid")
+__failure __msg("css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs")
 int BPF_PROG(iter_css_task_for_each)
 {
 	u64 cg_id = bpf_get_current_cgroup_id();
diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c
new file mode 100644
index 0000000000000000000000000000000000000000..193c0f8272d056f562266d891cdfd14c47c011e3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_precision.c
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 SUSE LLC */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0xfffffff8 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (87) r2 = -r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 8")
+__naked int bpf_neg(void)
+{
+	asm volatile (
+		"r2 = 8;"
+		"r2 = -r2;"
+		"if r2 != -8 goto 1f;"
+		"r1 = r10;"
+		"r1 += r2;"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0x0 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (d4) r2 = le16 r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 0")
+__naked int bpf_end_to_le(void)
+{
+	asm volatile (
+		"r2 = 0;"
+		"r2 = le16 r2;"
+		"if r2 != 0 goto 1f;"
+		"r1 = r10;"
+		"r1 += r2;"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0x0 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (dc) r2 = be16 r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 0")
+__naked int bpf_end_to_be(void)
+{
+	asm volatile (
+		"r2 = 0;"
+		"r2 = be16 r2;"
+		"if r2 != 0 goto 1f;"
+		"r1 = r10;"
+		"r1 += r2;"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+	defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
+	__clang_major__ >= 18
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0x0 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (d7) r2 = bswap16 r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 0")
+__naked int bpf_end_bswap(void)
+{
+	asm volatile (
+		"r2 = 0;"
+		"r2 = bswap16 r2;"
+		"if r2 != 0 goto 1f;"
+		"r1 = r10;"
+		"r1 += r2;"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+#endif /* v4 instruction */
diff --git a/tools/testing/selftests/bpf/verifier/bpf_st_mem.c b/tools/testing/selftests/bpf/verifier/bpf_st_mem.c
index 3af2501082b29b625f7de508059971cb2f996acb..b616575c3b00a5b74a5e4af180fe91004258e506 100644
--- a/tools/testing/selftests/bpf/verifier/bpf_st_mem.c
+++ b/tools/testing/selftests/bpf/verifier/bpf_st_mem.c
@@ -65,3 +65,35 @@
 	.expected_attach_type = BPF_SK_LOOKUP,
 	.runs = -1,
 },
+{
+	"BPF_ST_MEM stack imm sign",
+	/* Check if verifier correctly reasons about sign of an
+	 * immediate spilled to stack by BPF_ST instruction.
+	 *
+	 *   fp[-8] = -44;
+	 *   r0 = fp[-8];
+	 *   if r0 s< 0 goto ret0;
+	 *   r0 = -1;
+	 *   exit;
+	 * ret0:
+	 *   r0 = 0;
+	 *   exit;
+	 */
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, -44),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+	BPF_JMP_IMM(BPF_JSLT, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, -1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	/* Use prog type that requires return value in range [0, 1] */
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+	.result = VERBOSE_ACCEPT,
+	.runs = -1,
+	.errstr = "0: (7a) *(u64 *)(r10 -8) = -44        ; R10=fp0 fp-8_w=-44\
+	2: (c5) if r0 s< 0x0 goto pc+2\
+	R0_w=-44",
+},
diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
index 17c0f92ff160294705157a9448a4ec0a15400bca..c3ba40d0b9de4617eea41095d1a69fee2a872a98 100644
--- a/tools/testing/selftests/bpf/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -430,7 +430,7 @@ static void print_usage(void)
 
 static void read_args(int argc, char *argv[])
 {
-	char opt;
+	int opt;
 
 	while ((opt = getopt(argc, argv, "mh")) != -1) {
 		switch (opt) {