blob: 379f6a7ad72889cdd84d0e4f33c0fe0f2e9cc617 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
|
<think>
Okay, let's see. The user mentioned a bug in QEMU user-mode when using clang 17 and newer with the -fsanitize=function option. The issue is a segmentation fault (SEGV) when calling the TCG prologue.
First, I need to understand what's going on here. The -fsanitize=function flag is part of Clang's sanitizers, which probably instruments function calls for checking. TCG is Tiny Code Generator, which QEMU uses for dynamic translation. The prologue is the part of the generated code that sets up the function call.
The problem arises when these sanitizers interact with QEMU's TCG. Since the error happens during the execution of the generated code (prologue), it's likely related to how the code is generated or executed at runtime. The segmentation fault suggests an invalid memory access, which could be due to incorrect code generation by TCG when the sanitizer is active.
Looking at the categories: instruction, syscall, runtime. Instruction would be if there's a wrong machine instruction. Syscall relates to system calls. Runtime covers other runtime errors. Since the issue is about code execution and memory access during runtime, especially when a sanitizer modifies the code flow, the most fitting category is runtime.
</think>
runtime
|