Date: Mon, 8 Jun 2026 11:33:57 +0200 From: Mario Marietto <marietto2008@gmail.com> To: FreeBSD virtualization <freebsd-virtualization@freebsd.org>, =?UTF-8?Q?Corvin_K=C3=B6hne?= <corvink@freebsd.org>, =?UTF-8?Q?Corvin_K=C3=B6hne?= <c.koehne@beckhoff.com> Subject: How FLR has been implemented inside the Corvin's code for the nVidia GPU. Message-ID: <CA%2B1FSigzrr7_t6WnGAZirOCnfRpwXk%2Bks-654qvZc7yM9FyRDw@mail.gmail.com>
index | next in thread | raw e-mail
[-- Attachment #1 --] Hello Corvin and everyone. I'm continuing the development of the initial project of Abhinav Chavali, the VMM Accelerator support for QEMU : https://summerofcode.withgoogle.com/archive/2025/projects/lRkVElCJ It seems that it works fine,but I would like to know. How was FLR implemented in the code Corvin wrote to pass the NVIDIA GPU to a Linux-based VM? I ask because when I use the Corvin's patched bhyve, or perhaps his vmm, I don't see any system freezes when I load and unload the vmm module from memory. It used to happen at the beginning,I remember well, but later not anymore. However, when I do it with qemu accelerated with bhyve, the problem still occurs. I asked Claude to look into Corvin's code to understand how he handled it, but even after doing so, the problem persists. -- Mario. [-- Attachment #2 --] <div dir="ltr"><div>Hello Corvin and everyone.</div><div><br></div><div>I'm continuing the development of the initial project of Abhinav Chavali, the VMM Accelerator support for QEMU :<br> <br> <div class="gmail-bbCodeBlock gmail-bbCodeBlock--unfurl gmail-js-unfurl gmail-fauxBlockLink"> <div class="gmail-contentRow"> <div class="gmail-contentRow-main"><h3 class="gmail-contentRow-header gmail-js-unfurl-title"><a href="https://summerofcode.withgoogle.com/archive/2025/projects/lRkVElCJ">https://summerofcode.withgoogle.com/archive/2025/projects/lRkVElCJ</a></h3><br></div>; </div> </div>It seems that it works fine,but I would like to know.</div><div><br></div><div><span class="gmail-HwtZe" lang="en"><span class="gmail-jCAhz"><span class="gmail-ryNqvb">How was FLR implemented in the code Corvin wrote to pass the NVIDIA GPU to a Linux-based VM?</span></span> <span class="gmail-jCAhz gmail-ChMk0b"><span class="gmail-ryNqvb">I ask because when I use the Corvin's patched bhyve, or perhaps his vmm, I don't see any system freezes when I load and unload the vmm module from memory.</span></span> <span class="gmail-jCAhz"><span class="gmail-ryNqvb">It used to happen at the beginning,I remember well, but later not anymore.</span></span> <span class="gmail-jCAhz"><span class="gmail-ryNqvb">However, when I do it with qemu accelerated with bhyve, the problem still occurs.</span></span> <span class="gmail-jCAhz"><span class="gmail-ryNqvb">I asked Claude to look into Corvin's code to understand how he handled it, but even after doing so, the problem persists.</span></span></span><span class="gmail-ZSCsVd"></span><div class="gmail-OvtS8d"><span></span><span class="gmail-LdhArd"></span><span></span></div></div><br><span class="gmail_signature_prefix">-- </span><br><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature">Mario.<br></div></div>home | help
Want to link to this message? Use this
URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CA%2B1FSigzrr7_t6WnGAZirOCnfRpwXk%2Bks-654qvZc7yM9FyRDw>