blob: 4a4afbbcb360bdd1de09f5ddaaf2f6e9ef2fb22d (
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 is about user-mode or system-mode in QEMU. Let me start by understanding the problem.
The user mentioned they're using the `qemu-user` option `-strace -D <file>`, which isn't working as expected. They tried redirecting the strace output, but it's getting mixed with their program's stderr. So they used `-D` to log to a file, but that file was empty.
Looking into the source code, they found that instead of using `qemu_log`, the function `gemu_log` was being used for printing the strace output. That made me think maybe there was an issue with how logging is handled in this context.
They fixed it by replacing all instances of `gemu_log` with `qemu_log` and removed the declarations, which worked. The files they changed were `main.c` and `qemu.h`, both under the `linux-user` directory.
So, since they're working within `linux-user`, that's related to user-mode emulation in QEMU. User-mode deals with running binaries of different architectures without full OS virtualization, so this issue is about how strace logging works there.
System-mode would involve higher-level stuff like device emulation or full VMs, which doesn't seem relevant here. The problem was specific to the logging mechanism in user-mode processes.
</think>
user
|