blob: ee6a57e85e5329fb93f479317c047c48a2f0fc18 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
|
<think>
Okay, I need to classify this bug report as either 'user-mode' or 'system-mode'. Let's break down the information given.
The user is running QEMU in user mode because they're using commands like './qemu-i386 -d in_asm /bin/ls', which suggests they're executing a binary (like ls) under QEMU, not booting an entire OS. The issue reported is about incorrect section information in the log output when comparing two different versions of QEMU: 0.14.0 and 0.12.5.
The problem seems to be in how memory regions are being walked and logged. In the older version (0.12.5), the code correctly calculates end addresses, but in 0.14.0, there's a discrepancy. The user modified the code by changing how the shift is calculated, which fixed the output for them.
Looking at the change they made: in 0.14.0, they replaced (abi_ulong)i << V_L1_SHIFT with (abi_ulong)i << (V_L1_SHIFT + TARGET_PAGE_BITS). This indicates an issue in memory mapping during the execution of user-mode processes. The sections and their permissions are not being logged correctly, which is crucial for debugging user-space applications.
Since this involves how QEMU handles memory regions when running a user-space binary, it's related to user-mode emulation rather than system-level operations like hardware devices or OS booting. Therefore, the bug is in user-mode.
</think>
user
|