1
2
3
4
5
6
7
8
9
10
11
12
13
|
<think>
Okay, let's see. The user is reporting that Qemu crashes with a SIGFPE when certain trapping arithmetic operations are performed on the m68k target. They provided a C program and some assembly code as examples.
First, I need to figure out what's causing the crash. The problem occurs when the guest performs an arithmetic operation that traps. The SIGFPE is a floating-point exception, but in this case, it's related to integer division, specifically when dividing INT_MIN by -1. That would cause an overflow because in two's complement, that's undefined behavior in C and would trigger a trap on some architectures.
Looking at the example code: when you divide INT_MIN by -1, it's supposed to overflow. On the m68k, this would generate a trap. The question is whether Qemu is handling that trap correctly. Since Qemu is crashing with SIGFPE, it's possible that the emulator isn't properly handling the exception generated by the guest's arithmetic operation.
The user mentioned that this is specific to the m68k target. The assembly code provided uses 'divsl.l' which is a signed division instruction. If the division causes an overflow (like dividing INT_MIN by -1), the m68k would raise an exception. Qemu is supposed to emulate that exception handling, but instead, it's crashing.
Now, looking at the categories: instruction, syscall, or runtime. The problem is related to how Qemu handles a specific instruction (divsl.l) that causes an exception. The crash occurs when executing this instruction, so the issue is likely in the instruction emulation code. Therefore, the category should be 'instruction'.
</think>
instruction
|