blob: 3a3f99c837d1f937c713e6272c89a41b05d32387 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
|
<think>
Okay, I need to classify this bug report into one of the given categories: instruction, syscall, or runtime. The user provided a detailed description of the issue where qemu-user is hanging due to glib allocation problems during forking in multi-threaded environments.
Looking at the problem, it's happening during the execution when multiple threads and forking are involved. The hang occurs because glib's memory management isn't fork-safe, leading to deadlocks on mutexes. This isn't an issue with a specific instruction or a syscall itself but rather how resources are managed during runtime, especially after forking.
The workaround suggests using G_SLICE=always-malloc, which points towards issues in dynamic memory allocation and thread safety at runtime. The problem arises because the child process inherits some locked state from the parent, causing it to hang when accessing glib's structures.
So this isn't an instruction-level bug or a syscall issue. It's more about how the application handles resources and concurrency during runtime.
</think>
runtime
|