blob: ec61dd391424f28327852d462a044d076e4f5fcb (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
<think>
Alright, let's try to figure out whether this bug report is user-mode or system-mode related. The user provided a lot of information, including a stack trace from gdb and configuration details.
Looking at the crash, it mentions scsi_device_purge_requests() waiting indefinitely. SCSI devices are typically part of the system hardware emulation in QEMU. The code paths involved seem to be dealing with block I/O and device handling, which are lower-level operations.
The bug report includes terms like 'vhost-scsi support: YES', which suggests that it's related to virtualized storage devices. Since vhost-scsi is a kernel module used for high-performance SCSI device passthrough in system-mode emulation, this points towards system-mode issues.
Additionally, the configuration shows that system-mode emulation is enabled while user-mode is disabled. The target list includes x86_64-softmmu, which is a system emulator. This further indicates that the problem occurs in the context of emulating an entire computer system, including hardware devices like SCSI controllers.
The stack traces involve functions related to block layer and I/O handling, which are core components of QEMU's system emulation. The fact that aio_poll() is involved also suggests it's dealing with asynchronous I/O operations typical in system-mode where multiple virtual devices might be interacting.
Considering all these points—SCSI device handling, vhost-scsi support, and the configuration targeting system-mode—it's clear this bug is related to system-mode operation.
</think>
system
|