[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [PATCH] qga: Allow building of the guest agent without system emulat

From: Thomas Huth
Subject: Re: [PATCH] qga: Allow building of the guest agent without system emulators or tools
Date: Thu, 10 Nov 2022 09:35:31 +0100
User-agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101 Thunderbird/91.13.0

On 10/11/2022 06.49, Markus Armbruster wrote:
Philippe Mathieu-Daudé <philmd@linaro.org> writes:

On 9/11/22 18:37, Thomas Huth wrote:
If configuring with "--disable-system --disable-user --enable-guest-agent"
the linking currently fails with:

qga/qemu-ga.p/commands.c.o: In function `qmp_command_info':
build/../../home/thuth/devel/qemu/qga/commands.c:70: undefined reference to 
build/../../home/thuth/devel/qemu/qga/commands.c:71: undefined reference to 
build/../../home/thuth/devel/qemu/qga/commands.c:72: undefined reference to 
qga/qemu-ga.p/commands.c.o: In function `qmp_guest_info':
build/../../home/thuth/devel/qemu/qga/commands.c:82: undefined reference to 
qga/qemu-ga.p/commands.c.o: In function `qmp_guest_exec':
build/../../home/thuth/devel/qemu/qga/commands.c:410: undefined reference to 
qga/qemu-ga.p/channel-posix.c.o: In function `ga_channel_open':
build/../../home/thuth/devel/qemu/qga/channel-posix.c:214: undefined reference 
to `unix_listen'
build/../../home/thuth/devel/qemu/qga/channel-posix.c:228: undefined reference 
to `socket_parse'
build/../../home/thuth/devel/qemu/qga/channel-posix.c:234: undefined reference 
to `socket_listen'
qga/qemu-ga.p/commands-posix.c.o: In function `qmp_guest_file_write':
build/../../home/thuth/devel/qemu/qga/commands-posix.c:527: undefined reference 
to `qbase64_decode'

Let's make sure that we also compile and link the required files if
the system emulators have not been enabled.

Signed-off-by: Thomas Huth <thuth@redhat.com>

I wonder for how long this has been broken.

Should we add such a configuration to CI?

Some month ago, I'd say: Sure! ... but considering that gitlab now limits the available CI minutes and that apparently nobody really cares about this configuration (otherwise someone would have complained about this earlier), I think it's not that important to have a separate CI test for this configuration.


reply via email to

[Prev in Thread] Current Thread [Next in Thread]