blob: 7c92d0cb1bf34addca3d818296ea7c5f7062912b (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
<think>
Okay, I'm trying to figure out whether this bug report is related to user-mode or system-mode in QEMU. Let me start by understanding the problem described.
The issue is about building QEMU on a Darwin (which is macOS) PowerPC host and encountering compilation errors. The user provided some patches they applied earlier that fixed the build but caused the binary to crash upon launch. They suspect issues with assembler syntax, ABI compliance, or other fixes related to the Darwin ppc architecture.
Looking at the code snippets, the changes are in `safe-syscall.inc.S` for both ppc and ppc64 architectures. These files seem to handle system calls safely, which is a user-space concern because system calls are typically made by user applications to interact with the kernel. The functions like `safe_syscall_base`, `safe_syscall_start`, and `safe_syscall_end` are part of handling syscalls without interruptions from signals.
The problem arises during the build process for user-mode code, which suggests that this is a user-space issue rather than something related to system or hypervisor mode. The crash on launch likely happens in user-mode since it's about how the host processes make system calls.
Additionally, the patches involve adjusting assembler syntax and ensuring correct ABI compliance. Since ABIs are relevant for function calls and stack frames in user applications, this further points towards a user-mode issue.
So, considering all these factors—the build process, system call handling, and patches related to user-space assembly code—it seems clear that this bug is related to user-mode.
</think>
user
|