1
2
3
4
5
6
7
8
9
10
11
12
13
|
<think>
Alright, I need to classify this bug report into one of the given categories. Let me start by reading the problem carefully.
The issue is with the function `virtio_gpu_gl_update_cursor_data()`. It seems that this function ignores the cursor resource's pixel format. Instead of handling different formats properly, it uses `memcpy()`, which directly copies pointer data without considering the actual image structure or color space differences.
The user mentioned that this works fine if both the guest OS and display backend use the same pixel format but fails when they don't. Specifically, the SDL backend uses a different pixel format than GTK, leading to incorrect cursor colors depending on which backend is used.
Looking at the categories provided: mistranslation, assembly, other, device, graphic, socket, network, KVM, boot, vnc, debug, files, permissions, performance, kernel, peripherals, hypervisor.
The problem revolves around the Virtio GPU and display backends. Since it's related to cursor rendering and pixel formats in graphics output, this falls under the 'graphic' category.
</think>
graphic
|