blob: c6cfecf8b03e04e768a0c201e5e202085c171b6c (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
|
<think>
Okay, I need to classify this bug report as either user-mode or system-mode related. Let's break down the problem.
The issue is that when certain code is placed directly in the main function without encapsulating it in another function, the program hangs during execution on QEMU using RISC-V. The user provided a code snippet where moving the same operations into a helper function prevents the crash, but executing them inline causes a hang.
Considering possible causes:
1. **Toolchain Issue**: Maybe the compiler is generating incorrect machine code when optimizations are applied (-Os). This could be related to how variables or stack frames are handled differently in functions versus main.
2. **RTOS Porting Layer**: Even though no RTOS features are used here, there might be something in the port initialization affecting memory or context switching that only manifests when code is structured a certain way.
3. **QEMU Emulation Bug**: It's possible that QEMU has an issue handling certain instruction sequences or memory accesses under specific conditions, especially with RISC-V which is still being optimized in emulators.
The fact that the problem occurs at runtime and involves program flow suggests it's more about how the code executes rather than low-level hardware interactions. Since no OS calls or device drivers are involved here, it points away from system-mode issues which typically involve kernel operations or peripherals.
The issue seems to relate to code generation and execution within user-space applications, possibly involving function calls, stack management, or optimizations applied by the compiler. Therefore, this is more likely a user-mode problem.
</think>
user
|