blob: 97ed92e1efc146b4e74fa7407404e648fa9eb3cd (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
|
<think>
Alright, I need to classify the given bug report into one of the provided categories. Let me start by reading the bug report carefully.
The bug is about "migration wrong handling of KVM_GET_DIRTY_LOG ioctl". So it's related to the KVM (Kernel-based Virtual Machine) and involves an ioctl call which isn't being handled correctly during migration, specifically with ARM.
Looking at the code snippet provided:
static int kvm_physical_sync_dirty_bitmap(....)
{
....
if(kvm_vm_ioctl(s, KVM_GET_DIRTY_LOG, &d) == -1) {
- err out
}
... continue
}
The issue is that `kvm_vm_ioctl` can return values other than -1 upon failure, but the code only checks for -1. This leads to incorrect error handling when the ioctl call fails in a way that doesn't return -1, causing the migration to appear successful when it's actually failing to get the memslot dirty bitmap.
The categories provided include 'KVM' among others. Since this bug is directly related to KVM functionality and involves an ioctl specific to KVM (KVM_GET_DIRTY_LOG), it falls under the KVM category.
</think>
The bug report discusses incorrect handling of the `KVM_GET_DIRTY_LOG` ioctl call during migration, which relates specifically to the Kernel-based Virtual Machine (KVM) hypervisor. The issue is within the code that interacts with KVM's functionality, so the appropriate category is 'KVM'.
**Step-by-Step Explanation:**
1. **Identify Keywords:** The bug mentions "KVM_GET_DIRTY_LOG ioctl" and "migration," which are related to KVM.
2. **Understand the Context:** It involves an ioctl call specific to KVM, used during migration for dirty bitmap handling.
3. **Analyze the Issue:** The problem is in how errors from the ioctl call are handled within KVM's code.
4. **Map to Categories:** Since it's about KVM-specific functionality and error handling related to KVM ioctl calls, it fits under 'KVM'.
**Answer:**
KVM
|