blob: f8ff258d3c201d55bfcab47f6518bf27c36e1afc (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
|
<think>
Okay, let's see. The bug report is about an issue with the epoll_event structure on qemu-or1k (OpenRISC). The problem is that when using CMake with Qt5 automoc, it freezes during the build process. The user provided a patch that adds TARGET_OPENRISC to the condition for defining TARGET_EPOLL_PACKED.
So, the issue is related to the structure packing of epoll_event. The QEMU code for syscall handling has a structure definition for epoll_event, and on OpenRISC, it needs to be packed. The original code only applied packing for x86_64. The fix is adding OpenRISC to that condition, making the structure packed correctly.
Now, I need to classify this bug into one of the categories: instruction, syscall, or runtime.
The problem stems from how the epoll_event structure is defined in the syscall handling code. Since epoll is a system call in Linux, and the issue is about the structure's packing when handling syscalls in QEMU, this seems to be a syscall-related error. The structure is part of the syscall's data, so incorrect packing would cause data misalignment when the syscall is processed.
The infinite loop happens because the application is waiting for epoll events that aren't being processed correctly due to the structure's incorrect layout. This isn't a runtime error in the general sense but specifically tied to syscall handling. So the category should be syscall.
</think>
syscall
|