blob: d7e59663b38b3a9b518f1ecfed127831545d915f (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
<think>
Alright, I'm trying to help classify this bug report as either user-mode or system-mode related. Let me go through the details step by step.
The issue is that when running a FreeBSD-arm system using qemu-system-arm version 4.1.1 on Fedora 31, it's crashing with a SIGSEGV (segmentation fault) in helper_gvec_eq16. The command line provided shows various flags and devices being set up, including virtio-rng-device and an IDE drive.
The user mentions that qemu-3.0.1 worked without issues, but qemu-3.1.1 started failing with the same error. They're now reporting this as a bug in QEMU.
Now, to classify this, I need to understand what part of QEMU is causing the issue. The function helper_gvec_eq16 is part of the TCG (Translation-Caching Virtualization) runtime, which handles the translation and execution of guest CPU instructions in user mode. GVec functions are related to vector operations, so this is likely a low-level instruction that's crashing during the emulation.
Since the crash occurs within the QEMU process itself while emulating the ARM architecture, it's more about how QEMU translates and executes the guest code rather than any specific peripheral or device interaction. The error seems to stem from an issue in the TCG layer when handling vector comparisons, which is part of the CPU emulation.
Therefore, this bug is likely related to user-mode execution because it's happening during the translation and execution of guest instructions by QEMU, not necessarily involving higher-privilege operations or specific device drivers. It affects how the emulator processes the code from the FreeBSD guest OS.
</think>
user
|