blob: cfeef89f7904949fb19d0f9fc4a889fc59993764 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
|
<think>
Okay, let's see. The user is reporting a segfault in qemu-arm user mode after upgrading to version 2.11.x, specifically when using a uclibc-ng chroot. They mentioned that downgrading a certain commit that changed MAX_RESERVED_VA fixed the issue. The backtrace points to code execution functions in QEMU's TCG (Tiny Code Generator) part.
First, I need to figure out the category. The options are instruction, syscall, or runtime.
The problem seems to be related to code generation. The MAX_RESERVED_VA is likely a memory address reservation setting. The segfault occurs during execution of generated code (like in cpu_tb_exec), which is part of QEMU's dynamic translation. This isn't a syscall issue because the error is happening in the code generation buffer, which is part of the execution flow. It's not about a specific instruction either, but more about the memory layout or buffer management for generated code.
Since the error is happening during runtime execution of the translated code, the most fitting category would be 'runtime'. The segfault is due to the way memory is reserved and managed for code generation, which affects how QEMU runs the translated code on the host. Therefore, it's a runtime error.
</think>
runtime
|