1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
<think>
Okay, I need to classify this bug report into one of the given categories: mistranslation, assembly lowering, other, device, graphic, socket, network, KVM, boot, vnc, debug, files, permissions, performance, kernel, peripherals, hypervisor.
Looking at the problem description, it's about `tcg_gen_mulu2_i32` causing infinite recursion on a 32-bit host. The issue arises because `tcg_gen_mulu2_i32` calls `tcg_gen_mul_i64`, which in turn calls back to `tcg_gen_mulu2_i32`. This creates an infinite loop, leading to a crash.
The root cause is related to the TCG (Translation Common) code generator in QEMU. The function calls are misrouted because the necessary flags (`TCG_TARGET_HAS_mulu2_i32` and `TCG_TARGET_HAS_muluh_i32`) aren't properly checked at compile time. The current check only verifies if these flags are defined, not their actual values.
This seems to be an issue with how the TCG handles function calls between different integer sizes (like 32-bit vs 64-bit operations). It's not a problem in user-mode assembly translation but rather within the code generation process itself. Since it's about function call chains leading to recursion, it doesn't fit into categories like graphic or network.
The bug is more related to how QEMU generates and optimizes machine instructions during compilation, which falls under the 'assembly lowering' category. Assembly lowering involves converting higher-level operations (like in Intermediate Representation) into lower-level assembly code, ensuring that the generated code correctly maps to the target architecture without causing issues like infinite recursion.
So, considering all this, the appropriate category for this bug report is 'assembly'.
</think>
assembly
|