blob: ca298bd8f533687068ff2198c2b48bca70b70287 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
<think>
Okay, let me try to figure this out. So, the bug report is about QEMU crashing when running with a specific machine type and configuration. The problem occurs during device tree generation.
First, I see that the issue starts with `dtc` (device tree compiler) crashing. The error message mentions an assertion failure in `get_node_by_phandle` because it receives a phandle value of 0, which isn't expected unless fixups are needed, but they aren't happening here.
Looking deeper, the problem arises from the function `fdt_get_phandle(fdt, lpc_off)` returning 0. This happens when trying to set the interrupt-parent for the "isa-serial@i3f8" node to the phandle of "lpc@0". Since it can't find the phandle, it defaults to 0.
The user suggests that if they comment out the line setting the interrupt-parent in `pnv_dt_serial`, the crash doesn't happen. This implies that the issue is related to how the device tree nodes are being handled during compilation or generation.
QEMU's role here is in generating the device tree, and since the problem occurs when using the `-machine powernv` option, it's likely an issue with QEMU's handling of PowerPC (PPC) architecture, specifically with the device trees for that machine type.
The possible categories include 'hypervisor', which makes sense because QEMU acts as a hypervisor for PPC machines like powernv. Issues in device tree generation could be part of the hypervisor setup or management.
</think>
hypervisor
|