blob: 1c7eda2d5c03a0a8abc2e8a2a50133e6b117f295 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
|
<think>
Okay, I'm trying to figure out whether this QEMU bug is related to user-mode or system-mode. The problem occurs when hitting an instruction breakpoint on a memory address that's translated by two stages and not in the TLB. It fails at target/arm/ptw.c:301 with an assertion about ARMFault_None.
The user mentioned it started after upgrading from 7.1.0 to 7.2.0, pointing out a specific commit where the check for get_phys_addr_lpae changed. The commit involved changing a failure condition, which might have introduced this issue.
Now, I need to classify this bug as either 'user' or 'system'. User-mode typically deals with applications running on top of the OS, while system-mode involves lower-level things like device emulation and privileged operations.
Given that it's about memory translation (TLB misses) and faults during instruction execution, this seems related to how QEMU handles virtualization at a deeper level. The PTW (Page Table Walker) is part of the MMU simulation which is crucial for system-mode operations. The fault handling here likely affects how the CPU interacts with memory in a virtualized environment, which is more of a system-level concern.
Therefore, this bug is probably related to system-mode because it's dealing with lower-level memory management and privileged operations that are essential for running an entire OS or device emulation.
</think>
system
|