diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 01e203964892..cd191c5fdb0a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2917,7 +2917,13 @@ int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size,
 int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size);
 
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
-void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
+int bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
+s32 bpf_call_args_imm(s16 idx);
+#else
+static inline s32 bpf_call_args_imm(s16 idx)
+{
+	return 0;
+}
 #endif
 
 struct btf *bpf_get_btf_vmlinux(void);
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index b148f816f25b..185b2aa43a42 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -729,6 +729,7 @@ struct bpf_subprog_info {
 	 */
 	s16 fastcall_stack_off;
 	bool has_tail_call: 1;
+	bool might_throw: 1;
 	bool tail_call_reachable: 1;
 	bool has_ld_abs: 1;
 	bool is_cb: 1;
@@ -1308,6 +1309,7 @@ void bpf_fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask);
 bool bpf_subprog_is_global(const struct bpf_verifier_env *env, int subprog);
 
 int bpf_find_subprog(struct bpf_verifier_env *env, int off);
+bool bpf_is_throw_kfunc(struct bpf_insn *insn);
 int bpf_compute_const_regs(struct bpf_verifier_env *env);
 int bpf_prune_dead_branches(struct bpf_verifier_env *env);
 int bpf_check_cfg(struct bpf_verifier_env *env);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 1ec6d5ba64cc..88a241aac36a 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1151,9 +1151,6 @@ bool sk_filter_charge(struct sock *sk, struct sk_filter *fp);
 void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);
 
 u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
-#define __bpf_call_base_args \
-	((u64 (*)(u64, u64, u64, u64, u64, const struct bpf_insn *)) \
-	 (void *)__bpf_call_base)
 
 struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog);
 void bpf_jit_compile(struct bpf_prog *prog);
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 5e25e0353509..dfb2110ab733 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -827,7 +827,7 @@ const struct bpf_map_ops array_map_ops = {
 };
 
 const struct bpf_map_ops percpu_array_map_ops = {
-	.map_meta_equal = bpf_map_meta_equal,
+	.map_meta_equal = array_map_meta_equal,
 	.map_alloc_check = array_map_alloc_check,
 	.map_alloc = array_map_alloc,
 	.map_free = array_map_free,
diff --git a/kernel/bpf/cfg.c b/kernel/bpf/cfg.c
index 998f42a8189a..26d37066465f 100644
--- a/kernel/bpf/cfg.c
+++ b/kernel/bpf/cfg.c
@@ -64,11 +64,19 @@ static void mark_subprog_might_sleep(struct bpf_verifier_env *env, int off)
 	subprog->might_sleep = true;
 }
 
+static void mark_subprog_might_throw(struct bpf_verifier_env *env, int off)
+{
+	struct bpf_subprog_info *subprog;
+
+	subprog = bpf_find_containing_subprog(env, off);
+	subprog->might_throw = true;
+}
+
 /* 't' is an index of a call-site.
  * 'w' is a callee entry point.
  * Eventually this function would be called when env->cfg.insn_state[w] == EXPLORED.
  * Rely on DFS traversal order and absence of recursive calls to guarantee that
- * callee's change_pkt_data marks would be correct at that moment.
+ * callee's effect marks would be correct at that moment.
  */
 static void merge_callee_effects(struct bpf_verifier_env *env, int t, int w)
 {
@@ -78,6 +86,7 @@ static void merge_callee_effects(struct bpf_verifier_env *env, int t, int w)
 	callee = bpf_find_containing_subprog(env, w);
 	caller->changes_pkt_data |= callee->changes_pkt_data;
 	caller->might_sleep |= callee->might_sleep;
+	caller->might_throw |= callee->might_throw;
 }
 
 enum {
@@ -509,6 +518,8 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
 				mark_subprog_might_sleep(env, t);
 			if (ret == 0 && bpf_is_kfunc_pkt_changing(&meta))
 				mark_subprog_changes_pkt_data(env, t);
+			if (ret == 0 && bpf_is_throw_kfunc(insn))
+				mark_subprog_might_throw(env, t);
 		}
 		return visit_func_call_insn(t, insns, env, insn->src_reg == BPF_PSEUDO_CALL);
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 8b018ff48875..6aa2a8b24030 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1771,6 +1771,9 @@ static u32 abs_s32(s32 x)
 	return x >= 0 ? (u32)x : -(u32)x;
 }
 
+static u64 (*interpreters_args[])(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5,
+				  const struct bpf_insn *insn);
+
 /**
  *	___bpf_prog_run - run eBPF program on a given context
  *	@regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers
@@ -2077,10 +2080,9 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn)
 		CONT;
 
 	JMP_CALL_ARGS:
-		BPF_R0 = (__bpf_call_base_args + insn->imm)(BPF_R1, BPF_R2,
-							    BPF_R3, BPF_R4,
-							    BPF_R5,
-							    insn + insn->off + 1);
+		BPF_R0 = interpreters_args[insn->off](BPF_R1, BPF_R2, BPF_R3,
+						      BPF_R4, BPF_R5,
+						      insn + insn->imm + 1);
 		CONT;
 
 	JMP_TAIL_CALL: {
@@ -2394,13 +2396,22 @@ EVAL4(PROG_NAME_LIST, 416, 448, 480, 512)
 #undef PROG_NAME_LIST
 
 #ifdef CONFIG_BPF_SYSCALL
-void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth)
+int bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth)
 {
 	stack_depth = max_t(u32, stack_depth, 1);
-	insn->off = (s16) insn->imm;
-	insn->imm = interpreters_args[(round_up(stack_depth, 32) / 32) - 1] -
-		__bpf_call_base_args;
+	/* Prevent out-of-bounds read to interpreters_args */
+	if (stack_depth > MAX_BPF_STACK)
+		return -EINVAL;
+	insn->off = (round_up(stack_depth, 32) / 32) - 1;
 	insn->code = BPF_JMP | BPF_CALL_ARGS;
+	return 0;
+}
+
+s32 bpf_call_args_imm(s16 idx)
+{
+	if (WARN_ON_ONCE(idx < 0 || idx >= ARRAY_SIZE(interpreters_args)))
+		return 0;
+	return BPF_CALL_IMM(interpreters_args[idx]);
 }
 #endif
 #endif
diff --git a/kernel/bpf/fixups.c b/kernel/bpf/fixups.c
index fba9e8c00878..3692adf62558 100644
--- a/kernel/bpf/fixups.c
+++ b/kernel/bpf/fixups.c
@@ -1250,9 +1250,9 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		}
 		if (!bpf_pseudo_call(insn))
 			continue;
-		insn->off = env->insn_aux_data[i].call_imm;
-		subprog = bpf_find_subprog(env, i + insn->off + 1);
-		insn->imm = subprog;
+		insn->imm = env->insn_aux_data[i].call_imm;
+		subprog = bpf_find_subprog(env, i + insn->imm + 1);
+		insn->off = subprog;
 	}
 
 	prog->jited = 1;
@@ -1416,7 +1416,12 @@ int bpf_fixup_call_args(struct bpf_verifier_env *env)
 		depth = get_callee_stack_depth(env, insn, i);
 		if (depth < 0)
 			return depth;
-		bpf_patch_call_args(insn, depth);
+		err = bpf_patch_call_args(insn, depth);
+		if (err) {
+			verbose(env, "stack depth %d exceeds interpreter stack depth limit\n",
+				depth);
+			return err;
+		}
 	}
 	err = 0;
 #endif
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 2bb60200c266..b5314c9fed3c 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -4241,8 +4241,13 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_p,
 
 	data_len = __bpf_dynptr_size(data_ptr);
 	data = __bpf_dynptr_data(data_ptr, data_len);
+	if (!data)
+		return -EINVAL;
+
 	sig_len = __bpf_dynptr_size(sig_ptr);
 	sig = __bpf_dynptr_data(sig_ptr, sig_len);
+	if (!sig)
+		return -EINVAL;
 
 	return verify_pkcs7_signature(data, data_len, sig, sig_len,
 				      trusted_keyring->key,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a3c0214ca934..630d530782fe 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4919,6 +4919,29 @@ static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog,
 	return map;
 }
 
+static void prepare_dump_pseudo_call(struct bpf_insn *insn)
+{
+	s32 call_off = insn->imm;
+
+	/*
+	 * BPF_CALL_ARGS only exists for interpreter fallback.
+	 * 1. For interpreter (BPF_CALL_ARGS): insn->off is the index of
+	 *    interpreters_args array, so here using bpf_call_args_imm()
+	 *    to get the real address offset.
+	 * 2. For JIT (BPF_CALL): insn->off is the subprog id.
+	 */
+	if (insn->code == (BPF_JMP | BPF_CALL_ARGS))
+		insn->imm = bpf_call_args_imm(insn->off);
+	else
+		insn->imm = insn->off;
+
+	/* Avoid dumping a truncated and misleading pc-relative offset. */
+	if (call_off > S16_MAX || call_off < S16_MIN)
+		insn->off = 0;
+	else
+		insn->off = call_off;
+}
+
 static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog,
 					      const struct cred *f_cred)
 {
@@ -4944,6 +4967,9 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog,
 		}
 		if (code == (BPF_JMP | BPF_CALL) ||
 		    code == (BPF_JMP | BPF_CALL_ARGS)) {
+			/* Restore the legacy xlated dump layout. */
+			if (insns[i].src_reg == BPF_PSEUDO_CALL)
+				prepare_dump_pseudo_call(&insns[i]);
 			if (code == (BPF_JMP | BPF_CALL_ARGS))
 				insns[i].code = BPF_JMP | BPF_CALL;
 			if (!bpf_dump_raw_ok(f_cred))
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 69d75515ed3f..7fb88e1cd7c4 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -442,7 +442,6 @@ static bool is_dynptr_ref_function(enum bpf_func_id func_id)
 static bool is_sync_callback_calling_kfunc(u32 btf_id);
 static bool is_async_callback_calling_kfunc(u32 btf_id);
 static bool is_callback_calling_kfunc(u32 btf_id);
-static bool is_bpf_throw_kfunc(struct bpf_insn *insn);
 
 static bool is_bpf_wq_set_callback_kfunc(u32 btf_id);
 static bool is_task_work_add_kfunc(u32 func_id);
@@ -5405,7 +5404,7 @@ static int check_max_stack_depth_subprog(struct bpf_verifier_env *env, int idx,
 		if (bpf_pseudo_kfunc_call(insn + i) && !insn[i].off) {
 			bool err = false;
 
-			if (!is_bpf_throw_kfunc(insn + i))
+			if (!bpf_is_throw_kfunc(insn + i))
 				continue;
 			for (tmp = idx; tmp >= 0 && !err; tmp = dinfo[tmp].caller) {
 				if (subprog[tmp].is_cb) {
@@ -9499,6 +9498,9 @@ static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *ins
 	return 0;
 }
 
+static int process_bpf_exit_full(struct bpf_verifier_env *env,
+				 bool *do_print_state, bool exception_exit);
+
 static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			   int *insn_idx)
 {
@@ -9552,6 +9554,17 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
 		}
 
+		if (env->subprog_info[subprog].might_throw) {
+			struct bpf_verifier_state *branch;
+
+			branch = push_stack(env, *insn_idx + 1, *insn_idx, false);
+			if (IS_ERR(branch)) {
+				verbose(env, "failed to push state for global subprog exception path\n");
+				return PTR_ERR(branch);
+			}
+			return process_bpf_exit_full(env, NULL, true);
+		}
+
 		/* continue with next insn after call */
 		return 0;
 	}
@@ -11263,7 +11276,11 @@ BTF_ID(func, bpf_task_work_schedule_resume)
 BTF_ID(func, bpf_arena_alloc_pages)
 BTF_ID(func, bpf_arena_free_pages)
 BTF_ID(func, bpf_arena_reserve_pages)
+#ifdef CONFIG_BPF_EVENTS
 BTF_ID(func, bpf_session_is_return)
+#else
+BTF_ID_UNUSED
+#endif
 BTF_ID(func, bpf_stream_vprintk)
 BTF_ID(func, bpf_stream_print_stack)
 
@@ -11778,7 +11795,7 @@ static bool is_async_callback_calling_kfunc(u32 btf_id)
 	       is_task_work_add_kfunc(btf_id);
 }
 
-static bool is_bpf_throw_kfunc(struct bpf_insn *insn)
+bool bpf_is_throw_kfunc(struct bpf_insn *insn)
 {
 	return bpf_pseudo_kfunc_call(insn) && insn->off == 0 &&
 	       insn->imm == special_kfunc_list[KF_bpf_throw];
@@ -12968,8 +12985,6 @@ static int check_special_kfunc(struct bpf_verifier_env *env, struct bpf_kfunc_ca
 }
 
 static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name);
-static int process_bpf_exit_full(struct bpf_verifier_env *env,
-				 bool *do_print_state, bool exception_exit);
 
 static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			    int *insn_idx_p)
@@ -13350,7 +13365,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	if (meta.func_id == special_kfunc_list[KF_bpf_session_cookie])
 		env->prog->call_session_cookie = true;
 
-	if (is_bpf_throw_kfunc(insn))
+	if (bpf_is_throw_kfunc(insn))
 		return process_bpf_exit_full(env, NULL, true);
 
 	return 0;
diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
index cd5c2543f54d..9478b8f78f26 100644
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -592,13 +592,12 @@ static void emit_signature_match(struct bpf_gen *gen)
 		gen->hash_insn_offset[i] = gen->insn_cur - gen->insn_start;
 		emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_3, 0, 0, 0, 0, 0));
 
-		off =  -(gen->insn_cur - gen->insn_start - gen->cleanup_label) / 8 - 1;
+		off = -(gen->insn_cur - gen->insn_start - gen->cleanup_label) / 8 - 2;
 		if (is_simm16(off)) {
 			emit(gen, BPF_MOV64_IMM(BPF_REG_7, -EINVAL));
 			emit(gen, BPF_JMP_REG(BPF_JNE, BPF_REG_2, BPF_REG_3, off));
 		} else {
 			gen->error = -ERANGE;
-			emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, -1));
 		}
 	}
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c
index 8cd298b78e44..04aaf4c9cf5e 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c
@@ -14,7 +14,7 @@ static struct {
 	const char *prog_name;
 	int expected_runtime_err;
 } kfunc_dynptr_tests[] = {
-	{"dynptr_data_null", -EBADMSG},
+	{"dynptr_data_null", -EINVAL},
 };
 
 static bool kfunc_not_supported;
diff --git a/tools/testing/selftests/bpf/prog_tests/percpu_array_inner_map.c b/tools/testing/selftests/bpf/prog_tests/percpu_array_inner_map.c
new file mode 100644
index 000000000000..2a8b2381306b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/percpu_array_inner_map.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+/*
+ * Test that replacing an inner percpu array map with one that has different
+ * max_entries is rejected.  percpu_array_map_gen_lookup() inlines the
+ * template's index_mask, so allowing a smaller replacement would cause OOB.
+ */
+void test_percpu_array_inner_map(void)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, opts);
+	int outer_fd, tmpl_fd, good_fd, bad_fd, err;
+	int zero = 0;
+
+	/* Create template: percpu array with 8 entries */
+	tmpl_fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, "tmpl",
+				 sizeof(int), sizeof(long), 8, NULL);
+	if (!ASSERT_OK_FD(tmpl_fd, "create_tmpl"))
+		return;
+
+	/* Create outer array-of-maps using template */
+	opts.inner_map_fd = tmpl_fd;
+	outer_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY_OF_MAPS, "outer",
+				  sizeof(int), sizeof(int), 1, &opts);
+	if (!ASSERT_OK_FD(outer_fd, "create_outer"))
+		goto close_tmpl;
+
+	/* Insert template as initial inner map */
+	err = bpf_map_update_elem(outer_fd, &zero, &tmpl_fd, 0);
+	if (!ASSERT_OK(err, "insert_tmpl"))
+		goto close_outer;
+
+	/* Replacement with same max_entries should succeed */
+	good_fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, "good",
+				 sizeof(int), sizeof(long), 8, NULL);
+	if (!ASSERT_OK_FD(good_fd, "create_good"))
+		goto close_outer;
+
+	err = bpf_map_update_elem(outer_fd, &zero, &good_fd, 0);
+	ASSERT_OK(err, "replace_same_max_entries");
+	close(good_fd);
+
+	/* Replacement with fewer max_entries must fail */
+	bad_fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, "bad",
+				sizeof(int), sizeof(long), 2, NULL);
+	if (!ASSERT_OK_FD(bad_fd, "create_bad"))
+		goto close_outer;
+
+	err = bpf_map_update_elem(outer_fd, &zero, &bad_fd, 0);
+	ASSERT_ERR(err, "replace_smaller_max_entries");
+	close(bad_fd);
+
+close_outer:
+	close(outer_fd);
+close_tmpl:
+	close(tmpl_fd);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index a96b25ebff23..06cd24e37b3f 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -22,6 +22,7 @@
 #include "verifier_bswap.skel.h"
 #include "verifier_btf_ctx_access.skel.h"
 #include "verifier_btf_unreliable_prog.skel.h"
+#include "verifier_call_large_imm.skel.h"
 #include "verifier_cfg.skel.h"
 #include "verifier_cgroup_inv_retcode.skel.h"
 #include "verifier_cgroup_skb.skel.h"
@@ -170,6 +171,7 @@ void test_verifier_bpf_trap(void)             { RUN(verifier_bpf_trap); }
 void test_verifier_bswap(void)                { RUN(verifier_bswap); }
 void test_verifier_btf_ctx_access(void)       { RUN(verifier_btf_ctx_access); }
 void test_verifier_btf_unreliable_prog(void)  { RUN(verifier_btf_unreliable_prog); }
+void test_verifier_call_large_imm(void)       { RUN(verifier_call_large_imm); }
 void test_verifier_cfg(void)                  { RUN(verifier_cfg); }
 void test_verifier_cgroup_inv_retcode(void)   { RUN(verifier_cgroup_inv_retcode); }
 void test_verifier_cgroup_skb(void)           { RUN(verifier_cgroup_skb); }
diff --git a/tools/testing/selftests/bpf/progs/exceptions_fail.c b/tools/testing/selftests/bpf/progs/exceptions_fail.c
index 051e2b6f2694..ac44d60e5066 100644
--- a/tools/testing/selftests/bpf/progs/exceptions_fail.c
+++ b/tools/testing/selftests/bpf/progs/exceptions_fail.c
@@ -208,6 +208,28 @@ int reject_with_reference(void *ctx)
 	return 0;
 }
 
+__noinline int global_subprog_may_throw(struct __sk_buff *ctx)
+{
+	if (ctx->len)
+		bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("Unreleased reference")
+int reject_global_subprog_throw_with_reference(struct __sk_buff *ctx)
+{
+	struct foo *f;
+
+	f = bpf_obj_new(typeof(*f));
+	if (!f)
+		return 0;
+	if (ctx->protocol)
+		global_subprog_may_throw(ctx);
+	bpf_obj_drop(f);
+	return 0;
+}
+
 __noinline static int subprog_ref(struct __sk_buff *ctx)
 {
 	struct foo *f;
diff --git a/tools/testing/selftests/bpf/progs/verifier_call_large_imm.c b/tools/testing/selftests/bpf/progs/verifier_call_large_imm.c
new file mode 100644
index 000000000000..7998df07f6a6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_call_large_imm.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+int call_happened = 0;
+
+/*
+ * 32765 is the exact minimum number of padding instructions needed to
+ * trigger the verifier failure, because:
+ * 1. Counting the wrapper instructions around the padding block (one
+ *    "r0=0" and two "exit" instructions), the actual jump distance
+ *    evaluates to N + 3.
+ * 2. To overflow the s16 max bound (32767), we need N + 3 > 32767.
+ * Thus, N = 32765 is the exact minimum padding size required.
+ */
+static __attribute__((noinline)) void padding_subprog(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	".rept 32765;"
+	"r0 += 0;"
+	".endr;"
+	::: __clobber_all);
+}
+
+static __attribute__((noinline)) int target_subprog(void)
+{
+	/* Use volatile variable here to prevent optimization. */
+	volatile int magic_ret = 3;
+	return magic_ret;
+}
+
+SEC("syscall")
+__success __retval(3)
+int call_large_imm_test(void *ctx)
+{
+	/*
+	 * Landing pad to handle call error on kernel without the fix,
+	 * preventing kernel panic.
+	 */
+	asm volatile (
+	"r0 = 0;"
+	".rept 32768;"
+	"r0 += 0;"
+	".endr;"
+	::: __clobber_all);
+
+	/*
+	 * The call_happened variable is 1 only when the call insn wrongly
+	 * go back to the landing pad above.
+	 */
+	if (call_happened == 1) {
+		/* Use volatile variable here to prevent optimization. */
+		volatile int flag = -1;
+		return flag;
+	}
+
+	call_happened = 1;
+
+	padding_subprog();
+
+	return target_subprog();
+}
+
+char LICENSE[] SEC("license") = "GPL";