blob: 96b32a088a6dfe805617e17ada2369ce05da71e4 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
|
<think>
Okay, I need to figure out whether this bug report is classified as 'user-mode' or 'system-mode'. Let's break down the problem.
The issue occurs when executing a retf instruction in userspace with an invalid stack pointer. The guest OS (Linux) gets a wrong error code because bit 2 isn't set, which it uses to determine if the fault came from kernel space. This leads the kernel to panic, thinking it's handling a kernel fault when it's actually a user-space issue.
The reproduction steps involve compiling and running a simple C program that triggers this behavior. The problem arises in user-mode code execution because retf is causing an incorrect error code, leading the kernel (system-mode) to misbehave.
QEMU is involved as the emulator, but the bug affects how it handles user-space instructions. Since QEMU's handling of user-mode instructions leads to incorrect system-mode behavior, this seems like a problem in how the virtual CPU manages exceptions during user operations.
The classification should be based on where the issue primarily impacts. Even though it causes kernel panic (system), the root cause is in how user-mode instructions are processed.
</think>
user
|