blob: 5a45a7c592e1f9bccf1e1b86bc2140d956ccb8a7 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
|
<think>
Okay, I need to classify this bug report as either 'user-mode' or 'system-mode'. The issue is happening in QEMU when running a test case from the GCC testsuite, specifically gfortran's proc_ptr_51.f90.
Looking at the error message: "cpu_exec: Assertion !have_mmap_lock() failed". This seems to be related to how memory mappings are handled during execution. The problem occurs in the cpu-exec.c file, which is part of QEMU's TCG (Translation Control Graph) component.
The user provided a tarball with an executable and some libraries. They're running it under QEMU and seeing these assertion failures repeatedly. They noted that similar issues occur on native aarch64 and arm machines, but QEMU shouldn't crash or assert in such cases.
Now, thinking about user-mode vs system-mode: User-mode emulation deals with running applications without full OS support, while system-mode involves emulating the entire system including hardware devices and an operating system.
Since this test is using a set of shared libraries (libc, libgfortran, etc.) and seems to be trying to run a userland application in QEMU's environment, it's likely running in user-mode. The error relates to memory management during CPU execution, which is more about the application's behavior rather than system-level hardware emulation.
So I think this bug falls under 'user' mode.
</think>
The issue occurs when running a userland application using QEMU without full OS support, involving memory mapping assertions within the CPU execution context.
user
|