From dee4dcba78baf712cab403d47d9db319ab7f95d6 Mon Sep 17 00:00:00 2001 From: Christian Krinitsin Date: Thu, 3 Jul 2025 19:39:53 +0200 Subject: restructure results --- .../classifier/deepseek-r1:14b/reasoning/hypervisor/1324727 | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 results/classifier/deepseek-r1:14b/reasoning/hypervisor/1324727 (limited to 'results/classifier/deepseek-r1:14b/reasoning/hypervisor/1324727') diff --git a/results/classifier/deepseek-r1:14b/reasoning/hypervisor/1324727 b/results/classifier/deepseek-r1:14b/reasoning/hypervisor/1324727 new file mode 100644 index 00000000..7916b88d --- /dev/null +++ b/results/classifier/deepseek-r1:14b/reasoning/hypervisor/1324727 @@ -0,0 +1,11 @@ + +Okay, I need to classify the given bug report into one of the provided categories. The user mentioned that qemu-system-arm segfaults without KVM on ARM and works fine when KVM is enabled. They're running on an Odroid-XU with Debian Jessie armhf. + +Looking at the possible categories: kernel, hypervisor, device, etc. Since the issue occurs without KVM but not with it, it's likely related to how QEMU emulates things without hardware acceleration (KVM provides kernel-based virtualization). The segfault happens when running without KVM, so maybe a problem in the emulation code or how the CPU is being handled. + +The backtrace shows issues in cpu_tb_exec and cpu_arm_exec. These functions are part of the CPU execution loop in QEMU. A segmentation fault here suggests an issue with the translation buffer (TB) or instruction handling when not using KVM. + +So, since it's about the hypervisor mode (or lack thereof), the category should be 'hypervisor'. The problem arises without KVM, implying a bug in the non-KVM (user-mode) emulation which falls under hypervisor-related issues. + + +hypervisor \ No newline at end of file -- cgit 1.4.1