blob: 3fd73e77d207dbc9941789996967e45c496ee44e (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
|
<think>
Okay, let's see. The user mentioned a bug in QEMU related to the waitid system call. The issue is that when info.si_pid is zero, the target siginfo is left uninitialized.
First, I need to figure out which category this falls into. The options are instruction, syscall, or runtime.
The bug is about the waitid system call not initializing the siginfo structure properly under certain conditions. Since waitid is a system call, this seems like it's related to how the syscall is handled. The problem isn't with the instruction itself (like a wrong opcode or something), but rather how the syscall's data structure is managed. So it's probably a syscall error.
Runtime errors are more about issues during program execution that aren't directly tied to specific syscalls, like memory leaks or logic errors. Since this is specifically a problem with the waitid syscall's handling, the correct category should be syscall.
</think>
syscall
|