blob: f07a0e028be50b33a390e03cfbcf5698db2f603f (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
<think>
Okay, so I'm trying to figure out whether this bug report about pwrite() behavior in QEMU's aarch64-linux-user is related to user-mode or system-mode emulation.
First, let me understand the problem. The user provided a test program that uses pwrite with NULL buffer and len=0. On native x86_64 and native aarch64 systems, it returns 0, which seems correct because writing zero bytes should return zero without error. However, when running under QEMU's aarch64-linux-user emulator, it returns -1, indicating an error.
The bug is in the user-mode emulation because pwrite is a system call that interacts with file descriptors and memory. In this case, since the program is being run in user mode (as indicated by "aarch64-linux-user"), QEMU is emulating the system calls made by the user-space application.
I don't think it's related to system-mode because system-mode would involve more about running a full OS with device emulation and such. Here, the issue is specific to how a system call (pwrite) is handled in user-mode, where the application is directly interacting with QEMU as if it were the kernel.
So, this bug should be classified under 'user' because it's about the user-mode system call handling.
</think>
The bug report pertains to the user-mode emulation of the pwrite() system call within QEMU. It specifically deals with how the emulator handles a system call from a user-space application, making it a user-mode issue.
**Answer:** user
|