blob: e251a57f888712190c0d488c5aae3d9f7cb92e4f (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
|
<think>
Okay, I'm trying to classify this bug report into one of three categories: instruction, syscall, or runtime. Let's break down what the user described.
The issue occurs when using QEMU with specific options and then attaching GDB. The command `qemu-x86_64` is run with `-E LD_PROFILE=libc.so.6` which seems to enable profiling for a library, `-g 12345` sets up a gdbserver, and `-L /` specifies the root directory. Then, in another window, GDB connects to this server and continues execution.
The problem is that QEMU segfaults when `sigprof` is passed to GDB. The user mentions that they patched `gdbstub.c` to ignore `SIGPROF`, which stops the segmentation fault but means they can't catch profiling signals in GDB anymore.
So, what's happening here? Profiling involves sending `SIGPROF` signals when certain events happen (like function calls). When QEMU is running under a debugger (GDB), it might mishandle these signals. The issue isn't with the instruction execution or a specific system call but rather how signals are being processed at runtime.
The crash happens during runtime due to improper handling of `SIGPROF` signals, which suggests that the bug falls under runtime errors.
</think>
runtime
|