blob: 3afcf14468b48b567bebbc03fbee45db451de36b (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
<think>
Okay, I need to figure out whether this bug report is related to user-mode or system-mode in QEMU.
The issue is about the `follow_path()` function in `util/path.c` not handling "/" correctly when running gdbserver under QEMU. The problem arises during `__getcwd`, where it calls `lstat("/")`. In QEMU, `lstat` forwards this to `follow_path()`, which returns `QEMU_LD_PREFIX` instead of "/", causing inconsistencies.
I know that user-mode emulation deals with processes and system calls from the guest OS without full hardware virtualization. It uses software to translate certain system calls. System-mode involves running a full VM with virtualized hardware.
Since the problem is about handling paths in QEMU's process, specifically how `lstat` translates path requests, it relates to how user-space applications interact with the emulated environment. This doesn't involve lower-level hardware or device emulation but rather the file system handling within user processes.
So, this issue falls under user-mode.
</think>
The bug report is about how QEMU handles file paths in a user application, specifically when using `lstat("/")`. Since it's related to process execution and file system interactions without involving low-level hardware virtualization, it's classified as 'user'.
**Answer:** user
|