bpf: Fix array bounds error with may_goto

may_goto uses an additional 8 bytes on the stack, which causes the
interpreters[] array to go out of bounds when calculating index by
stack_size.

1. If a BPF program is rewritten, re-evaluate the stack size. For non-JIT
cases, reject loading directly.

2. For non-JIT cases, calculating interpreters[idx] may still cause
out-of-bounds array access, and just warn about it.

3. For jit_requested cases, the execution of bpf_func also needs to be
warned. So move the definition of function __bpf_prog_ret0_warn out of
the macro definition CONFIG_BPF_JIT_ALWAYS_ON.

Reported-by: syzbot+d2a2c639d03ac200a4f1@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/bpf/0000000000000f823606139faa5d@google.com/
Fixes: 011832b97b ("bpf: Introduce may_goto instruction")
Signed-off-by: Jiayuan Chen <mrpre@163.com>
Link: https://lore.kernel.org/r/20250214091823.46042-2-mrpre@163.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

kernel/bpf/core.c

@@ -2290,17 +2290,18 @@ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth)
 	insn->code = BPF_JMP | BPF_CALL_ARGS;
 }
 #endif
-#else
+#endif
+
 static unsigned int __bpf_prog_ret0_warn(const void *ctx,
 					 const struct bpf_insn *insn)
 {
 	/* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON
-	 * is not working properly, so warn about it!
+	 * is not working properly, or interpreter is being used when
+	 * prog->jit_requested is not 0, so warn about it!
 	 */
 	WARN_ON_ONCE(1);
 	return 0;
 }
-#endif
 
 bool bpf_prog_map_compatible(struct bpf_map *map,
 			     const struct bpf_prog *fp)
@@ -2380,8 +2381,18 @@ static void bpf_prog_select_func(struct bpf_prog *fp)
 {
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
 	u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
+	u32 idx = (round_up(stack_depth, 32) / 32) - 1;
 
-	fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
+	/* may_goto may cause stack size > 512, leading to idx out-of-bounds.
+	 * But for non-JITed programs, we don't need bpf_func, so no bounds
+	 * check needed.
+	 */
+	if (!fp->jit_requested &&
+	    !WARN_ON_ONCE(idx >= ARRAY_SIZE(interpreters))) {
+		fp->bpf_func = interpreters[idx];
+	} else {
+		fp->bpf_func = __bpf_prog_ret0_warn;
+	}
 #else
 	fp->bpf_func = __bpf_prog_ret0_warn;
 #endif

kernel/bpf/verifier.c

@@ -21903,6 +21903,13 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 		if (subprogs[cur_subprog + 1].start == i + delta + 1) {
 			subprogs[cur_subprog].stack_depth += stack_depth_extra;
 			subprogs[cur_subprog].stack_extra = stack_depth_extra;
+
+			stack_depth = subprogs[cur_subprog].stack_depth;
+			if (stack_depth > MAX_BPF_STACK && !prog->jit_requested) {
+				verbose(env, "stack size %d(extra %d) is too large\n",
+					stack_depth, stack_depth_extra);
+				return -EINVAL;
+			}
 			cur_subprog++;
 			stack_depth = subprogs[cur_subprog].stack_depth;
 			stack_depth_extra = 0;