blob: b6628d673c4d805edcbd7547abc3d83677c54f26 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
<think>
Okay, so I need to classify this bug report as either 'user-mode' or 'system-mode'. The issue involves the M68K FPU in QEMU. Let me think through what each mode entails.
User-mode issues usually relate to how applications run on top of the OS. They involve things like process management, file access, and application crashes. System-mode deals with lower-level stuff like hardware emulation, device drivers, and kernel functions.
In this case, the problem is about QEMU's FPU handling for M68K targets. The issue arises when compiling a Pascal program that uses floating-point operations. The test shows incorrect behavior where an infinity value becomes NaN after a function call.
The root cause seems to be in QEMU's softfloat implementation, specifically how it handles the floatx80_infinity_low value for M68K. This affects the FPU state during emulation. Since this is part of QEMU's core handling of the CPU and floating-point operations, it's a lower-level issue.
This problem isn't about an application crashing or malfunctioning in user space but rather about how the virtualized CPU processes certain floating-point values. It impacts the correctness of the emulated environment at the processor level.
Therefore, this bug is more related to system-mode because it involves the correct emulation of hardware (the FPU) and affects the state that's managed at a lower level than user applications.
</think>
system
|